mirror of
https://github.com/graphdeco-inria/gaussian-splatting
synced 2025-06-26 18:18:11 +00:00
add lidar depth with mesh
This commit is contained in:
Xun2001
parent
81590b1f57
commit
b787991bb2
4
.gitmodules
vendored
4
.gitmodules
vendored
@ -4,10 +4,10 @@
|
||||
[submodule "submodules/diff-gaussian-rasterization"]
|
||||
path = submodules/diff-gaussian-rasterization
|
||||
url = https://github.com/graphdeco-inria/diff-gaussian-rasterization.git
|
||||
branch = dr_aa
|
||||
branch = 3dgs_accel # branch = dr_aa
|
||||
[submodule "SIBR_viewers"]
|
||||
path = SIBR_viewers
|
||||
url = https://gitlab.inria.fr/sibr/sibr_core.git
|
||||
[submodule "submodules/fused-ssim"]
|
||||
path = submodules/fused-ssim
|
||||
url = https://github.com/rahul-goel/fused-ssim.git
|
||||
url = https://github.com/rahul-goel/fused-ssim.git
|
||||
@ -56,10 +56,13 @@ class ModelParams(ParamGroup):
|
||||
self.train_test_exp = False
|
||||
self.data_device = "cuda"
|
||||
self.eval = False
|
||||
# xy-new
|
||||
self.skybox_locked = False
|
||||
self.skybox_num = 0
|
||||
self.scaffold_file = ""
|
||||
self.bounds_file = ""
|
||||
self.is_lidar_depth = False
|
||||
self.lidar_depth_max = 30.0
|
||||
super().__init__(parser, "Loading Parameters", sentinel) # add parameters into parser
|
||||
|
||||
def extract(self, args):
|
||||
|
||||
@ -20,7 +20,8 @@ class Camera(nn.Module):
|
||||
def __init__(self, resolution, colmap_id, R, T, FoVx, FoVy, depth_params, image, invdepthmap,
|
||||
image_name, uid,
|
||||
trans=np.array([0.0, 0.0, 0.0]), scale=1.0, data_device = "cuda",
|
||||
train_test_exp = False, is_test_dataset = False, is_test_view = False
|
||||
train_test_exp = False, is_test_dataset = False, is_test_view = False,
|
||||
is_lidar_depth = False, max_depth = 30.0
|
||||
):
|
||||
super(Camera, self).__init__()
|
||||
|
||||
@ -39,13 +40,13 @@ class Camera(nn.Module):
|
||||
print(f"[Warning] Custom device {data_device} failed, fallback to default cuda device" )
|
||||
self.data_device = torch.device("cuda")
|
||||
|
||||
resized_image_rgb = PILtoTorch(image, resolution)
|
||||
resized_image_rgb = PILtoTorch(image, resolution)# [3,h,w]
|
||||
gt_image = resized_image_rgb[:3, ...]
|
||||
self.alpha_mask = None
|
||||
if resized_image_rgb.shape[0] == 4:
|
||||
self.alpha_mask = resized_image_rgb[3:4, ...].to(self.data_device)
|
||||
else:
|
||||
self.alpha_mask = torch.ones_like(resized_image_rgb[0:1, ...].to(self.data_device))
|
||||
self.alpha_mask = torch.ones_like(resized_image_rgb[0:1, ...].to(self.data_device))# [1,h,w] all 1
|
||||
|
||||
if train_test_exp and is_test_view:
|
||||
if is_test_dataset:
|
||||
@ -61,8 +62,19 @@ class Camera(nn.Module):
|
||||
self.depth_reliable = False
|
||||
if invdepthmap is not None:
|
||||
self.depth_mask = torch.ones_like(self.alpha_mask)
|
||||
self.invdepthmap = cv2.resize(invdepthmap, resolution)
|
||||
self.invdepthmap[self.invdepthmap < 0] = 0
|
||||
|
||||
# xy-new lidar depth to invdepth
|
||||
if is_lidar_depth:
|
||||
depth_raw = invdepthmap
|
||||
depth_lin = depth_raw / 255.0 * max_depth
|
||||
mask_np = depth_lin > 0
|
||||
invdepth_lidar = np.zeros_like(depth_lin)
|
||||
invdepth_lidar[mask_np] = 1.0 / (depth_lin[mask_np] + 1e-6)
|
||||
|
||||
self.depth_mask = torch.from_numpy(mask_np).to(self.data_device)
|
||||
|
||||
self.invdepthmap = cv2.resize(invdepth_lidar, resolution)
|
||||
self.invdepthmap[self.invdepthmap < 0] = 0
|
||||
self.depth_reliable = True
|
||||
|
||||
if depth_params is not None:
|
||||
@ -73,9 +85,9 @@ class Camera(nn.Module):
|
||||
if depth_params["scale"] > 0:
|
||||
self.invdepthmap = self.invdepthmap * depth_params["scale"] + depth_params["offset"]
|
||||
|
||||
if self.invdepthmap.ndim != 2:
|
||||
self.invdepthmap = self.invdepthmap[..., 0]
|
||||
self.invdepthmap = torch.from_numpy(self.invdepthmap[None]).to(self.data_device)
|
||||
if self.invdepthmap.ndim != 2: # [h,w,3]
|
||||
self.invdepthmap = self.invdepthmap[..., 0] # [h,w]
|
||||
self.invdepthmap = torch.from_numpy(self.invdepthmap[None]).to(self.data_device) # [1,h,w]
|
||||
|
||||
self.zfar = 100.0
|
||||
self.znear = 0.01
|
||||
|
||||
@ -198,7 +198,7 @@ def training(dataset, opt, pipe, testing_iterations, saving_iterations, checkpoi
|
||||
relevant = (gaussians._opacity.grad != 0).squeeze() # points - opacity gradients != 0
|
||||
gaussians.optimizer.step(relevant, gaussians.get_xyz.shape[0]) # no densification so need step relevant points
|
||||
gaussians.optimizer.zero_grad(set_to_none = True)
|
||||
|
||||
|
||||
if (iteration in checkpoint_iterations):
|
||||
print("\n[ITER {}] Saving Checkpoint".format(iteration))
|
||||
torch.save((gaussians.capture(), iteration), scene.model_path + "/chkpnt" + str(iteration) + ".pth")
|
||||
|
||||
@ -24,6 +24,9 @@ def loadCam(args, id, cam_info, resolution_scale, is_nerf_synthetic, is_test_dat
|
||||
try:
|
||||
if is_nerf_synthetic:
|
||||
invdepthmap = cv2.imread(cam_info.depth_path, -1).astype(np.float32) / 512
|
||||
elif args.is_lidar_depth:
|
||||
raw_uint8 = cv2.imread(cam_info.depth_path, 0).astype(np.float32)
|
||||
invdepthmap = raw_uint8 # to filter mask in Camera class
|
||||
else:
|
||||
invdepthmap = cv2.imread(cam_info.depth_path, -1).astype(np.float32) / float(2**16)
|
||||
|
||||
@ -64,7 +67,8 @@ def loadCam(args, id, cam_info, resolution_scale, is_nerf_synthetic, is_test_dat
|
||||
FoVx=cam_info.FovX, FoVy=cam_info.FovY, depth_params=cam_info.depth_params,
|
||||
image=image, invdepthmap=invdepthmap,
|
||||
image_name=cam_info.image_name, uid=id, data_device=args.data_device,
|
||||
train_test_exp=args.train_test_exp, is_test_dataset=is_test_dataset, is_test_view=cam_info.is_test)
|
||||
train_test_exp=args.train_test_exp, is_test_dataset=is_test_dataset, is_test_view=cam_info.is_test,
|
||||
is_lidar_depth=args.is_lidar_depth,max_depth=args.lidar_depth_max)
|
||||
|
||||
def cameraList_from_camInfos(cam_infos, resolution_scale, args, is_nerf_synthetic, is_test_dataset):
|
||||
camera_list = []
|
||||
|
||||
733
xy_utils/experiment.ipynb
Normal file
733
xy_utils/experiment.ipynb
Normal file
@ -0,0 +1,733 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b66179c8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1.预处理数据"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "533db061",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1.1 对点云数据进行处理 - 滤除环视范围外过远的点"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "864843b2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"1. 解析 images.txt，计算所有相机在世界坐标系下的光心（位姿）。 \n",
|
||||
"2. 使用 Open3D 加载 .pcd 点云，并基于与最近相机光心的距离进行滤除。 \n",
|
||||
"3. 输出相机光心的范围（坐标轴最小/最大值）以及被滤除的点云数量。 \n",
|
||||
"4. 将保留的点云按 COLMAP points3D.txt 格式保存，并额外生成一个 PLY 文件，其中红色标记被删除的点，原色保留未删除点。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5dc3ac56",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### ipynb内部函数 -- 未进行地面与boundingbox对齐"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cc2e8c18",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import open3d as o3d\n",
|
||||
"from scipy.spatial.transform import Rotation as R\n",
|
||||
"\n",
|
||||
"def filter_point_cloud(images_txt, pcd_path, output_points_txt, output_points_ply, output_ply_path):\n",
|
||||
" \"\"\"\n",
|
||||
" 根据相机位姿过滤点云，并保存结果。\n",
|
||||
"\n",
|
||||
" Args:\n",
|
||||
" images_txt (str): 包含相机位姿的 images.txt 文件路径。\n",
|
||||
" pcd_path (str): 点云文件路径。\n",
|
||||
" output_points_txt (str): 保存过滤后点云的 points3D.txt 文件路径。\n",
|
||||
" output_ply_path (str): 保存带颜色标记的 PLY 文件路径。\n",
|
||||
" \"\"\"\n",
|
||||
" def load_camera_centers(images_txt):\n",
|
||||
" centers = []\n",
|
||||
" with open(images_txt, 'r') as f:\n",
|
||||
" for line in f:\n",
|
||||
" if line.startswith('#') or len(line.strip()) == 0:\n",
|
||||
" continue\n",
|
||||
" elems = line.strip().split()\n",
|
||||
" if len(elems) < 10:\n",
|
||||
" continue\n",
|
||||
" qw, qx, qy, qz = map(float, elems[1:5])\n",
|
||||
" tx, ty, tz = map(float, elems[5:8])\n",
|
||||
" rot = R.from_quat([qx, qy, qz, qw]).as_matrix()\n",
|
||||
" center = -rot.T @ np.array([tx, ty, tz])\n",
|
||||
" centers.append(center)\n",
|
||||
" return np.array(centers)\n",
|
||||
"\n",
|
||||
" # 1. 加载相机中心\n",
|
||||
" camera_centers = load_camera_centers(images_txt)\n",
|
||||
"\n",
|
||||
" # 2. 计算平均中心和最大偏移\n",
|
||||
" center_mean = camera_centers.mean(axis=0)\n",
|
||||
" offsets = np.abs(camera_centers - center_mean)\n",
|
||||
" max_offset = offsets.max(axis=0)\n",
|
||||
"\n",
|
||||
" # 3. 加载点云\n",
|
||||
" pcd = o3d.io.read_point_cloud(pcd_path)\n",
|
||||
" points = np.asarray(pcd.points)\n",
|
||||
" colors = np.asarray(pcd.colors) if pcd.has_colors() else np.ones_like(points)\n",
|
||||
"\n",
|
||||
" # 4. 构建包围盒并裁剪点云\n",
|
||||
" min_bound = center_mean - max_offset - 15\n",
|
||||
" max_bound = center_mean + max_offset + 15\n",
|
||||
" aabb = o3d.geometry.AxisAlignedBoundingBox(min_bound, max_bound)\n",
|
||||
" pcd_cropped = pcd.crop(aabb)\n",
|
||||
"\n",
|
||||
" # 5. 统计信息\n",
|
||||
" total_points = len(points)\n",
|
||||
" kept_points = np.asarray(pcd_cropped.points)\n",
|
||||
" kept_colors = np.asarray(pcd_cropped.colors) if pcd_cropped.has_colors() else np.ones_like(kept_points)\n",
|
||||
" removed_mask = np.ones(total_points, dtype=bool)\n",
|
||||
" kept_indices = aabb.get_point_indices_within_bounding_box(pcd.points)\n",
|
||||
" removed_mask[kept_indices] = False\n",
|
||||
" removed_points = points[removed_mask]\n",
|
||||
" removed_colors = colors[removed_mask]\n",
|
||||
"\n",
|
||||
" print(\"相机中心范围：\")\n",
|
||||
" print(f\" X: [{min_bound[0]:.3f}, {max_bound[0]:.3f}]\")\n",
|
||||
" print(f\" Y: [{min_bound[1]:.3f}, {max_bound[1]:.3f}]\")\n",
|
||||
" print(f\" Z: [{min_bound[2]:.3f}, {max_bound[2]:.3f}]\")\n",
|
||||
" print(f\"总点数：{total_points}\")\n",
|
||||
" print(f\"保留点数：{len(kept_points)}\")\n",
|
||||
" print(f\"删除点数：{len(removed_points)}\")\n",
|
||||
"\n",
|
||||
" # 6. 保存 points3D.txt (速度太慢，直接使用 ply )\n",
|
||||
" with open(output_points_txt, \"w\") as f:\n",
|
||||
" f.write(\"# 3D point list with one line of data per point:\\n\")\n",
|
||||
" f.write(\"# POINT3D_ID, X, Y, Z, R, G, B, ERROR, TRACK[]\\n\")\n",
|
||||
" for idx, (pt, col) in enumerate(zip(kept_points, kept_colors), start=1):\n",
|
||||
" r, g, b = (col * 255).astype(int)\n",
|
||||
" f.write(f\"{idx} {pt[0]:.6f} {pt[1]:.6f} {pt[2]:.6f} {r} {g} {b} 0\\n\")\n",
|
||||
" # 保存为 ply 文件\n",
|
||||
" pcd_kept = o3d.geometry.PointCloud()\n",
|
||||
" pcd_kept.points = o3d.utility.Vector3dVector(kept_points)\n",
|
||||
" pcd_kept.colors = o3d.utility.Vector3dVector(kept_colors)\n",
|
||||
" o3d.io.write_point_cloud(output_points_ply, pcd_kept)\n",
|
||||
" print(\"保留的点云已保存为 {output_points_ply}\")\n",
|
||||
" \n",
|
||||
" # 7. 保存带颜色的 PLY 文件\n",
|
||||
" all_points = np.vstack((kept_points, removed_points))\n",
|
||||
" removed_colors_red = np.tile([1.0, 0.0, 0.0], (len(removed_points), 1))\n",
|
||||
" all_colors = np.vstack((kept_colors, removed_colors_red))\n",
|
||||
" pcd_all = o3d.geometry.PointCloud()\n",
|
||||
" pcd_all.points = o3d.utility.Vector3dVector(all_points)\n",
|
||||
" pcd_all.colors = o3d.utility.Vector3dVector(all_colors)\n",
|
||||
" o3d.io.write_point_cloud(output_ply_path, pcd_all)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "80b924be",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"相机中心范围：\n",
|
||||
" X: [-0.200, 28.270]\n",
|
||||
" Y: [-16.082, 1.699]\n",
|
||||
" Z: [-9.392, 0.714]\n",
|
||||
"总点数：16404321\n",
|
||||
"保留点数：10684495\n",
|
||||
"删除点数：5719826\n",
|
||||
"保留的点云已保存为 {output_points_ply}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"folder_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results'\n",
|
||||
"\n",
|
||||
"images_txt = os.path.join(folder_path, 'sparse/0/images.txt')\n",
|
||||
"pcd_path = os.path.join(folder_path, 'pcd/all_raw_points.pcd')\n",
|
||||
"output_points_ply = os.path.join(folder_path, 'pcd/points3D.ply')\n",
|
||||
"vis_ply_path = os.path.join(folder_path, 'pcd/vis_filter.ply')\n",
|
||||
"output_points_txt = os.path.join(folder_path, 'pcd/points3D.txt')\n",
|
||||
"filter_point_cloud(images_txt,pcd_path,output_points_txt, output_points_ply,vis_ply_path)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1a4206e8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### 调用 crop_points.py 文件"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8d8c55ed",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"总点数：16404321，保留：15254842，删除：1149479\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"!python crop_points.py \\\n",
|
||||
" --images_txt /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/sparse/0/images.txt \\\n",
|
||||
" --pcd_path /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/all_raw_points.pcd \\\n",
|
||||
" --output_points_txt /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/points3D.txt \\\n",
|
||||
" --output_ply /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/filtered_colored.ply \\\n",
|
||||
" --margin 10.0"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "651ed72f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1.2 利用体素化降采样"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "56f5cba7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"raw points len : 16404321\n",
|
||||
"downsample points len : 4671298\n",
|
||||
"降采样后的点云已保存到 /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points_0.05.ply，体素大小：0.05\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from tools.points_utils import voxel_downsample_and_save\n",
|
||||
"\n",
|
||||
"voxel_size = 0.05\n",
|
||||
"folder_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results'\n",
|
||||
"input_ply_path = os.path.join(folder_path,'pcd/points3D.ply')\n",
|
||||
"output_ply_path = os.path.join(folder_path,f'pcd/points3D_{voxel_size}.ply')\n",
|
||||
"input_ply_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.ply'\n",
|
||||
"output_ply_path = f'/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points_{voxel_size}.ply'\n",
|
||||
"\n",
|
||||
"voxel_downsample_and_save(voxel_size, input_ply_path, output_ply_path) # ply downsample to ply\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d1df326d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "8544bb3e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Jupyter environment detected. Enabling Open3D WebVisualizer.\n",
|
||||
"[Open3D INFO] WebRTC GUI backend enabled.\n",
|
||||
"[Open3D INFO] WebRTCWindowSystem: HTTP handshake server disabled.\n",
|
||||
"Converted /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.pcd to /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.ply\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# pcd 2 ply\n",
|
||||
"# 将原pcd点云，转换为ply点云\n",
|
||||
"from tools.points_utils import pcd_2_ply\n",
|
||||
"pcd_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.pcd'\n",
|
||||
"ply_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.ply'\n",
|
||||
"\n",
|
||||
"pcd_2_ply(pcd_file,ply_file)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "2bf16bb1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Jupyter environment detected. Enabling Open3D WebVisualizer.\n",
|
||||
"[Open3D INFO] WebRTC GUI backend enabled.\n",
|
||||
"[Open3D INFO] WebRTCWindowSystem: HTTP handshake server disabled.\n",
|
||||
"正在写入COLMAP TXT文件: /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/points3D_filter_white.txt\n",
|
||||
"Converted /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/sparse/0/points3D_filter.ply to Colmap TXT in: /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/points3D_filter_white.txt\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# pcd 2 txt\n",
|
||||
"from tools.points_utils import pcd_2_colmap_txt\n",
|
||||
"pcd_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/sparse/0/points3D_filter.ply'\n",
|
||||
"txt_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/points3D_filter_white.txt'\n",
|
||||
"\n",
|
||||
"pcd_2_colmap_txt(pcd_file, txt_file, is_white=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6fd0b306",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"选择一个合适的 points3D.ply 文件复制到 sparse/0 下"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "22e87bd3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1.2 Resize for more images"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "91ce4cb8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import cv2\n",
|
||||
"from tqdm import tqdm\n",
|
||||
"\n",
|
||||
"def resize_images(input_dir, output_dir, extensions):\n",
|
||||
" \"\"\"\n",
|
||||
" 读取输入文件夹中的所有图片，调整为1/2大小后保存到输出文件夹\n",
|
||||
" \n",
|
||||
" Args:\n",
|
||||
" input_dir: 输入图片文件夹路径\n",
|
||||
" output_dir: 输出图片文件夹路径\n",
|
||||
" extensions: 支持的图片扩展名列表\n",
|
||||
" \"\"\"\n",
|
||||
" # 确保输出目录存在\n",
|
||||
" os.makedirs(output_dir, exist_ok=True)\n",
|
||||
" \n",
|
||||
" # 获取所有图片文件\n",
|
||||
" image_files = []\n",
|
||||
" for file in os.listdir(input_dir):\n",
|
||||
" if any(file.lower().endswith(ext) for ext in extensions):\n",
|
||||
" image_files.append(file)\n",
|
||||
" \n",
|
||||
" if not image_files:\n",
|
||||
" print(f\"在 {input_dir} 中未找到支持的图片文件\")\n",
|
||||
" return\n",
|
||||
" \n",
|
||||
" print(f\"找到 {len(image_files)} 张图片\")\n",
|
||||
" \n",
|
||||
" # 处理每张图片\n",
|
||||
" count = 0\n",
|
||||
" for file in tqdm(image_files, desc=\"处理中\"):\n",
|
||||
" input_path = os.path.join(input_dir, file)\n",
|
||||
" output_path = os.path.join(output_dir, file)\n",
|
||||
" \n",
|
||||
" try:\n",
|
||||
" # 读取图片\n",
|
||||
" img = cv2.imread(input_path)\n",
|
||||
" if img is None:\n",
|
||||
" print(f\"警告: 无法读取图片 {input_path}，跳过\")\n",
|
||||
" continue\n",
|
||||
" \n",
|
||||
" # 获取原始尺寸\n",
|
||||
" height, width = img.shape[:2]\n",
|
||||
" \n",
|
||||
" # 计算新尺寸\n",
|
||||
" new_width = width // 2\n",
|
||||
" new_height = height // 2\n",
|
||||
" \n",
|
||||
" # 调整尺寸\n",
|
||||
" resized_img = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_AREA)\n",
|
||||
" \n",
|
||||
" # 保存图片\n",
|
||||
" cv2.imwrite(output_path, resized_img)\n",
|
||||
" \n",
|
||||
" # 输出尺寸信息\n",
|
||||
" if count == 0:\n",
|
||||
" print(f\"{file}: {width}x{height} -> {new_width}x{new_height}\")\n",
|
||||
" count += 1\n",
|
||||
" except Exception as e:\n",
|
||||
" print(f\"错误: 处理图片 {input_path} 时出错: {str(e)}\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e9b4da36",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"input_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01/depth_maps'\n",
|
||||
"output_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01/depth_maps_2'\n",
|
||||
"exts = ['jpg','jpeg','png']\n",
|
||||
"\n",
|
||||
"resize_images(input_path, output_path, exts)\n",
|
||||
"print(\"所有图片处理完成！\") "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3830cb91",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 2. LIVO2和Colmap的重建对比实验"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7dd6ff70",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"colmap无法恢复相机位姿；所以这里我们使用livo2恢复位姿后，用colmap 进行三角测量获取关键点\n",
|
||||
"https://www.cnblogs.com/Todd-Qi/p/15080968.html"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4ad9f127",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 2.1 基于Livo2位姿进行稀疏重建"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "40e8c7f1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"colmap无法恢复相机位姿；所以这里我们使用livo2恢复位姿后，用colmap 进行三角测量获取关键点\n",
|
||||
"https://www.cnblogs.com/Todd-Qi/p/15080968.html"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "497d715a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"1. 准备来自Livo2的位姿和相机数据 cameras.txt, images.txt\n",
|
||||
" 将内参(camera intrinsics) 放入cameras.txt， 外参(camera extrinsics)放入 images.txt , points3D.txt 为空 \n",
|
||||
" - images.txt 中全部 0.0 0.0 -1 删除; \n",
|
||||
" - points3D.txt 内容清空;\n",
|
||||
" - cameras.txt 中的内参进行修改 (对输入图像全部进行了 resize 操作，因此需要修改相机内参，将fx, fy, cx, cy 都除以2)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "497596e0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"2. 特征匹配与特征提取 \n",
|
||||
"``` bash\n",
|
||||
" colmap feature_extractor \\\n",
|
||||
" --database_path /path/to/project/database.db \\ \n",
|
||||
" --image_path /path/to/project/images\n",
|
||||
"```\n",
|
||||
"``` bash\n",
|
||||
" colmap exhaustive_matcher \\\n",
|
||||
" --database_path /path/to/project/database.db\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "590c5ba8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"3. 三角化重建 (保存的点云和其他文件均为bin格式)\n",
|
||||
"``` bash\n",
|
||||
" colmap point_triangulator \\\n",
|
||||
" --database_path /path/to/project/database.db \\\n",
|
||||
" --image_path /path/to/project/images \\\n",
|
||||
" --input_path /path/to/sparse_model \\\n",
|
||||
" --output_path /path/to/triangulated_model\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"查看txt结果\n",
|
||||
"``` bash\n",
|
||||
" colmap model_converter \\\n",
|
||||
" --input_path 0 \\\n",
|
||||
" --output_path 0_txt_from_livo2 \\\n",
|
||||
" --output_type TXT\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6c2b853f",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d359ac68",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"4. 稠密重建(optional)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "77250b4b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 3.训练"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d44f71f7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# baseline raw gs for training\n",
|
||||
"!CUDA_VISIBLE_DEVICES=1 python train.py \\\n",
|
||||
" -s data/tree_01_livo2 \\\n",
|
||||
" -m data/tree_01_livo2/outputs/3dgs_baseline\n",
|
||||
" \n",
|
||||
"# render\n",
|
||||
"!CUDA_VISIBLE_DEVICES=1 python render.py \\\n",
|
||||
" -s data/tree_01_colmap \\\n",
|
||||
" -m data/tree_01_colmap/outputs/3dgs_baseline "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a363d15d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 4.深度实验"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "1de51e3b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"--- depth_maps_2文件夹 ---\n",
|
||||
"找到图片：00144.png\n",
|
||||
"分辨率：1024 x 768 像素\n",
|
||||
"通道数：3\n",
|
||||
"通道说明：三通道（RGB）\n",
|
||||
"--- images我文件夹 ---\n",
|
||||
"找到图片：00144.png\n",
|
||||
"分辨率：1024 x 768 像素\n",
|
||||
"通道数：3\n",
|
||||
"通道说明：三通道（RGB）\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# 一、确认图像与深度图像尺寸是否一致\n",
|
||||
"from tools.images_utils import get_first_image_info\n",
|
||||
"\n",
|
||||
"folder_path = \"/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_save_w_depth/depth_maps_2\"\n",
|
||||
"print(\"--- depth_maps_2文件夹 ---\")\n",
|
||||
"get_first_image_info(folder_path)\n",
|
||||
"folder_path = \"/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3_depth/images\"\n",
|
||||
"print(\"--- images我文件夹 ---\")\n",
|
||||
"get_first_image_info(folder_path)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "6ee3b672",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"成功生成 JSON 文件：/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3_depth/sparse/0/depth_params.json\n",
|
||||
"共处理 539 个 PNG 文件\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# 2.在 sparse/0 下生成一个 depth_params.json\n",
|
||||
"\n",
|
||||
"# 示例数据:\n",
|
||||
"# {\n",
|
||||
"# \"DSC_3893\": {\n",
|
||||
"# \"scale\": 50.55648822378238,\n",
|
||||
"# \"offset\": 0.01793079636288747\n",
|
||||
"# },\n",
|
||||
"# \"DSC_3902\": {\n",
|
||||
"# \"scale\": 56.80526691363168,\n",
|
||||
"# \"offset\": 0.027163276135205097\n",
|
||||
"# }\n",
|
||||
"# }\n",
|
||||
"\n",
|
||||
"from tools.images_utils import generate_depth_params_json\n",
|
||||
"import os\n",
|
||||
"\n",
|
||||
"folder_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3_depth/'\n",
|
||||
"PNG_FOLDER = os.path.join(folder_path, 'depth_maps')\n",
|
||||
"OUTPUT_PATH = os.path.join(folder_path,\"sparse/0/depth_params.json\")\n",
|
||||
"# 生成 JSON 文件\n",
|
||||
"generate_depth_params_json(PNG_FOLDER, OUTPUT_PATH)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b337a10c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# 重命名 删去 -final的后缀\n",
|
||||
"from tools.images_utils import batch_rename_files\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"FOLDER_PATH = \"/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3_depth/depth_maps\" # 请替换为实际的文件夹路径\n",
|
||||
"batch_rename_files(FOLDER_PATH)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5f60df4e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# 如果有深度mesh缺失\n",
|
||||
"# ~/git_project/livo2-data-utils/10-Mesh-acc$ \n",
|
||||
"# python demo-acc.py -i \\\n",
|
||||
"# /home/qinllgroup/hongxiangyu/git_project/livo2-data-utils/10-Mesh-acc/data/delete \\\n",
|
||||
"# -o /home/qinllgroup/hongxiangyu/git_project/livo2-data-utils/10-Mesh-acc/data/delete \\\n",
|
||||
"# --max_edge 15\n",
|
||||
"\n",
|
||||
"from tools.images_utils import resize_image\n",
|
||||
"\n",
|
||||
"input_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_save_w_depth/depth_maps/00466-final.png'\n",
|
||||
"output_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_save_w_depth/depth_maps_2/00466.png'\n",
|
||||
"resize_image(input_path, output_path, scale=2, quality=100)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "024d1b19",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# 3. 训练深度mask\n",
|
||||
"!CUDA_VISIBLE_DEVICES=1 python train.py \\\n",
|
||||
" -s data/tree_01_livo2 \\\n",
|
||||
" -d data/tree_01_livo2/depth_map \\\n",
|
||||
" -m data/tree_01_livo2/outputs/3dgs_baseline"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "254f6278",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"成功将图片从 2048x1536 缩小到 1024x768\n",
|
||||
"保存路径: /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_save_w_depth/depth_maps_2/00466.png\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_save_w_depth/depth_maps_2/00466.png'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "66d0f159",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 4.1 深度读取"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7406df01",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 5.可视化TensorBoard"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9b0acade",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.18"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@ -2,578 +2,19 @@
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b66179c8",
|
||||
"id": "bf253aab",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 1.预处理数据"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "533db061",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1.1 对点云数据进行处理 - 滤除环视范围外过远的点"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "864843b2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"1. 解析 images.txt，计算所有相机在世界坐标系下的光心（位姿）。 \n",
|
||||
"2. 使用 Open3D 加载 .pcd 点云，并基于与最近相机光心的距离进行滤除。 \n",
|
||||
"3. 输出相机光心的范围（坐标轴最小/最大值）以及被滤除的点云数量。 \n",
|
||||
"4. 将保留的点云按 COLMAP points3D.txt 格式保存，并额外生成一个 PLY 文件，其中红色标记被删除的点，原色保留未删除点。"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5dc3ac56",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### ipynb内部函数 -- 未进行地面与boundingbox对齐"
|
||||
"# 基于CUDA的KNN计算"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "cc2e8c18",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import numpy as np\n",
|
||||
"import open3d as o3d\n",
|
||||
"from scipy.spatial.transform import Rotation as R\n",
|
||||
"\n",
|
||||
"def filter_point_cloud(images_txt, pcd_path, output_points_txt, output_points_ply, output_ply_path):\n",
|
||||
" \"\"\"\n",
|
||||
" 根据相机位姿过滤点云，并保存结果。\n",
|
||||
"\n",
|
||||
" Args:\n",
|
||||
" images_txt (str): 包含相机位姿的 images.txt 文件路径。\n",
|
||||
" pcd_path (str): 点云文件路径。\n",
|
||||
" output_points_txt (str): 保存过滤后点云的 points3D.txt 文件路径。\n",
|
||||
" output_ply_path (str): 保存带颜色标记的 PLY 文件路径。\n",
|
||||
" \"\"\"\n",
|
||||
" def load_camera_centers(images_txt):\n",
|
||||
" centers = []\n",
|
||||
" with open(images_txt, 'r') as f:\n",
|
||||
" for line in f:\n",
|
||||
" if line.startswith('#') or len(line.strip()) == 0:\n",
|
||||
" continue\n",
|
||||
" elems = line.strip().split()\n",
|
||||
" if len(elems) < 10:\n",
|
||||
" continue\n",
|
||||
" qw, qx, qy, qz = map(float, elems[1:5])\n",
|
||||
" tx, ty, tz = map(float, elems[5:8])\n",
|
||||
" rot = R.from_quat([qx, qy, qz, qw]).as_matrix()\n",
|
||||
" center = -rot.T @ np.array([tx, ty, tz])\n",
|
||||
" centers.append(center)\n",
|
||||
" return np.array(centers)\n",
|
||||
"\n",
|
||||
" # 1. 加载相机中心\n",
|
||||
" camera_centers = load_camera_centers(images_txt)\n",
|
||||
"\n",
|
||||
" # 2. 计算平均中心和最大偏移\n",
|
||||
" center_mean = camera_centers.mean(axis=0)\n",
|
||||
" offsets = np.abs(camera_centers - center_mean)\n",
|
||||
" max_offset = offsets.max(axis=0)\n",
|
||||
"\n",
|
||||
" # 3. 加载点云\n",
|
||||
" pcd = o3d.io.read_point_cloud(pcd_path)\n",
|
||||
" points = np.asarray(pcd.points)\n",
|
||||
" colors = np.asarray(pcd.colors) if pcd.has_colors() else np.ones_like(points)\n",
|
||||
"\n",
|
||||
" # 4. 构建包围盒并裁剪点云\n",
|
||||
" min_bound = center_mean - max_offset - 15\n",
|
||||
" max_bound = center_mean + max_offset + 15\n",
|
||||
" aabb = o3d.geometry.AxisAlignedBoundingBox(min_bound, max_bound)\n",
|
||||
" pcd_cropped = pcd.crop(aabb)\n",
|
||||
"\n",
|
||||
" # 5. 统计信息\n",
|
||||
" total_points = len(points)\n",
|
||||
" kept_points = np.asarray(pcd_cropped.points)\n",
|
||||
" kept_colors = np.asarray(pcd_cropped.colors) if pcd_cropped.has_colors() else np.ones_like(kept_points)\n",
|
||||
" removed_mask = np.ones(total_points, dtype=bool)\n",
|
||||
" kept_indices = aabb.get_point_indices_within_bounding_box(pcd.points)\n",
|
||||
" removed_mask[kept_indices] = False\n",
|
||||
" removed_points = points[removed_mask]\n",
|
||||
" removed_colors = colors[removed_mask]\n",
|
||||
"\n",
|
||||
" print(\"相机中心范围：\")\n",
|
||||
" print(f\" X: [{min_bound[0]:.3f}, {max_bound[0]:.3f}]\")\n",
|
||||
" print(f\" Y: [{min_bound[1]:.3f}, {max_bound[1]:.3f}]\")\n",
|
||||
" print(f\" Z: [{min_bound[2]:.3f}, {max_bound[2]:.3f}]\")\n",
|
||||
" print(f\"总点数：{total_points}\")\n",
|
||||
" print(f\"保留点数：{len(kept_points)}\")\n",
|
||||
" print(f\"删除点数：{len(removed_points)}\")\n",
|
||||
"\n",
|
||||
" # 6. 保存 points3D.txt (速度太慢，直接使用 ply )\n",
|
||||
" with open(output_points_txt, \"w\") as f:\n",
|
||||
" f.write(\"# 3D point list with one line of data per point:\\n\")\n",
|
||||
" f.write(\"# POINT3D_ID, X, Y, Z, R, G, B, ERROR, TRACK[]\\n\")\n",
|
||||
" for idx, (pt, col) in enumerate(zip(kept_points, kept_colors), start=1):\n",
|
||||
" r, g, b = (col * 255).astype(int)\n",
|
||||
" f.write(f\"{idx} {pt[0]:.6f} {pt[1]:.6f} {pt[2]:.6f} {r} {g} {b} 0\\n\")\n",
|
||||
" # 保存为 ply 文件\n",
|
||||
" pcd_kept = o3d.geometry.PointCloud()\n",
|
||||
" pcd_kept.points = o3d.utility.Vector3dVector(kept_points)\n",
|
||||
" pcd_kept.colors = o3d.utility.Vector3dVector(kept_colors)\n",
|
||||
" o3d.io.write_point_cloud(output_points_ply, pcd_kept)\n",
|
||||
" print(\"保留的点云已保存为 {output_points_ply}\")\n",
|
||||
" \n",
|
||||
" # 7. 保存带颜色的 PLY 文件\n",
|
||||
" all_points = np.vstack((kept_points, removed_points))\n",
|
||||
" removed_colors_red = np.tile([1.0, 0.0, 0.0], (len(removed_points), 1))\n",
|
||||
" all_colors = np.vstack((kept_colors, removed_colors_red))\n",
|
||||
" pcd_all = o3d.geometry.PointCloud()\n",
|
||||
" pcd_all.points = o3d.utility.Vector3dVector(all_points)\n",
|
||||
" pcd_all.colors = o3d.utility.Vector3dVector(all_colors)\n",
|
||||
" o3d.io.write_point_cloud(output_ply_path, pcd_all)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "80b924be",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"相机中心范围：\n",
|
||||
" X: [-0.200, 28.270]\n",
|
||||
" Y: [-16.082, 1.699]\n",
|
||||
" Z: [-9.392, 0.714]\n",
|
||||
"总点数：16404321\n",
|
||||
"保留点数：10684495\n",
|
||||
"删除点数：5719826\n",
|
||||
"保留的点云已保存为 {output_points_ply}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"folder_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results'\n",
|
||||
"\n",
|
||||
"images_txt = os.path.join(folder_path, 'sparse/0/images.txt')\n",
|
||||
"pcd_path = os.path.join(folder_path, 'pcd/all_raw_points.pcd')\n",
|
||||
"output_points_ply = os.path.join(folder_path, 'pcd/points3D.ply')\n",
|
||||
"vis_ply_path = os.path.join(folder_path, 'pcd/vis_filter.ply')\n",
|
||||
"output_points_txt = os.path.join(folder_path, 'pcd/points3D.txt')\n",
|
||||
"filter_point_cloud(images_txt,pcd_path,output_points_txt, output_points_ply,vis_ply_path)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1a4206e8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"#### 调用 crop_points.py 文件"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8d8c55ed",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"总点数：16404321，保留：15254842，删除：1149479\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"!python crop_points.py \\\n",
|
||||
" --images_txt /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/sparse/0/images.txt \\\n",
|
||||
" --pcd_path /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/all_raw_points.pcd \\\n",
|
||||
" --output_points_txt /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/points3D.txt \\\n",
|
||||
" --output_ply /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/filtered_colored.ply \\\n",
|
||||
" --margin 10.0"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "651ed72f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1.2 利用体素化降采样"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "56f5cba7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"raw points len : 16404321\n",
|
||||
"downsample points len : 4671298\n",
|
||||
"降采样后的点云已保存到 /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points_0.05.ply，体素大小：0.05\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from tools.points_utils import voxel_downsample_and_save\n",
|
||||
"\n",
|
||||
"voxel_size = 0.05\n",
|
||||
"folder_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results'\n",
|
||||
"input_ply_path = os.path.join(folder_path,'pcd/points3D.ply')\n",
|
||||
"output_ply_path = os.path.join(folder_path,f'pcd/points3D_{voxel_size}.ply')\n",
|
||||
"input_ply_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.ply'\n",
|
||||
"output_ply_path = f'/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points_{voxel_size}.ply'\n",
|
||||
"\n",
|
||||
"voxel_downsample_and_save(voxel_size, input_ply_path, output_ply_path) # ply downsample to ply\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d1df326d",
|
||||
"id": "1ad23d69",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "8544bb3e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Jupyter environment detected. Enabling Open3D WebVisualizer.\n",
|
||||
"[Open3D INFO] WebRTC GUI backend enabled.\n",
|
||||
"[Open3D INFO] WebRTCWindowSystem: HTTP handshake server disabled.\n",
|
||||
"Converted /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.pcd to /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.ply\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# pcd 2 ply\n",
|
||||
"# 将原pcd点云，转换为ply点云\n",
|
||||
"from tools.points_utils import pcd_2_ply\n",
|
||||
"pcd_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.pcd'\n",
|
||||
"ply_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/sparse/0/raw/all_raw_points.ply'\n",
|
||||
"\n",
|
||||
"pcd_2_ply(pcd_file,ply_file)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "2bf16bb1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Jupyter environment detected. Enabling Open3D WebVisualizer.\n",
|
||||
"[Open3D INFO] WebRTC GUI backend enabled.\n",
|
||||
"[Open3D INFO] WebRTCWindowSystem: HTTP handshake server disabled.\n",
|
||||
"正在写入COLMAP TXT文件: /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/points3D_filter_white.txt\n",
|
||||
"Converted /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/sparse/0/points3D_filter.ply to Colmap TXT in: /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/points3D_filter_white.txt\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# pcd 2 txt\n",
|
||||
"from tools.points_utils import pcd_2_colmap_txt\n",
|
||||
"pcd_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/sparse/0/points3D_filter.ply'\n",
|
||||
"txt_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/points3D_filter_white.txt'\n",
|
||||
"\n",
|
||||
"pcd_2_colmap_txt(pcd_file, txt_file, is_white=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6fd0b306",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"选择一个合适的 points3D.ply 文件复制到 sparse/0 下"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "22e87bd3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 1.2 Resize for more images"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "91ce4cb8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import cv2\n",
|
||||
"from tqdm import tqdm\n",
|
||||
"\n",
|
||||
"def resize_images(input_dir, output_dir, extensions):\n",
|
||||
" \"\"\"\n",
|
||||
" 读取输入文件夹中的所有图片，调整为1/2大小后保存到输出文件夹\n",
|
||||
" \n",
|
||||
" Args:\n",
|
||||
" input_dir: 输入图片文件夹路径\n",
|
||||
" output_dir: 输出图片文件夹路径\n",
|
||||
" extensions: 支持的图片扩展名列表\n",
|
||||
" \"\"\"\n",
|
||||
" # 确保输出目录存在\n",
|
||||
" os.makedirs(output_dir, exist_ok=True)\n",
|
||||
" \n",
|
||||
" # 获取所有图片文件\n",
|
||||
" image_files = []\n",
|
||||
" for file in os.listdir(input_dir):\n",
|
||||
" if any(file.lower().endswith(ext) for ext in extensions):\n",
|
||||
" image_files.append(file)\n",
|
||||
" \n",
|
||||
" if not image_files:\n",
|
||||
" print(f\"在 {input_dir} 中未找到支持的图片文件\")\n",
|
||||
" return\n",
|
||||
" \n",
|
||||
" print(f\"找到 {len(image_files)} 张图片\")\n",
|
||||
" \n",
|
||||
" # 处理每张图片\n",
|
||||
" count = 0\n",
|
||||
" for file in tqdm(image_files, desc=\"处理中\"):\n",
|
||||
" input_path = os.path.join(input_dir, file)\n",
|
||||
" output_path = os.path.join(output_dir, file)\n",
|
||||
" \n",
|
||||
" try:\n",
|
||||
" # 读取图片\n",
|
||||
" img = cv2.imread(input_path)\n",
|
||||
" if img is None:\n",
|
||||
" print(f\"警告: 无法读取图片 {input_path}，跳过\")\n",
|
||||
" continue\n",
|
||||
" \n",
|
||||
" # 获取原始尺寸\n",
|
||||
" height, width = img.shape[:2]\n",
|
||||
" \n",
|
||||
" # 计算新尺寸\n",
|
||||
" new_width = width // 2\n",
|
||||
" new_height = height // 2\n",
|
||||
" \n",
|
||||
" # 调整尺寸\n",
|
||||
" resized_img = cv2.resize(img, (new_width, new_height), interpolation=cv2.INTER_AREA)\n",
|
||||
" \n",
|
||||
" # 保存图片\n",
|
||||
" cv2.imwrite(output_path, resized_img)\n",
|
||||
" \n",
|
||||
" # 输出尺寸信息\n",
|
||||
" if count == 0:\n",
|
||||
" print(f\"{file}: {width}x{height} -> {new_width}x{new_height}\")\n",
|
||||
" count += 1\n",
|
||||
" except Exception as e:\n",
|
||||
" print(f\"错误: 处理图片 {input_path} 时出错: {str(e)}\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e9b4da36",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"input_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01/depth_maps'\n",
|
||||
"output_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01/depth_maps_2'\n",
|
||||
"exts = ['jpg','jpeg','png']\n",
|
||||
"\n",
|
||||
"resize_images(input_path, output_path, exts)\n",
|
||||
"print(\"所有图片处理完成！\") "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3830cb91",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 2. LIVO2和Colmap的重建对比实验"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7dd6ff70",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"colmap无法恢复相机位姿；所以这里我们使用livo2恢复位姿后，用colmap 进行三角测量获取关键点\n",
|
||||
"https://www.cnblogs.com/Todd-Qi/p/15080968.html"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4ad9f127",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 2.1 基于Livo2位姿进行稀疏重建"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "40e8c7f1",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"colmap无法恢复相机位姿；所以这里我们使用livo2恢复位姿后，用colmap 进行三角测量获取关键点\n",
|
||||
"https://www.cnblogs.com/Todd-Qi/p/15080968.html"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "497d715a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"1. 准备来自Livo2的位姿和相机数据 cameras.txt, images.txt\n",
|
||||
" 将内参(camera intrinsics) 放入cameras.txt， 外参(camera extrinsics)放入 images.txt , points3D.txt 为空 \n",
|
||||
" - images.txt 中全部 0.0 0.0 -1 删除; \n",
|
||||
" - points3D.txt 内容清空;\n",
|
||||
" - cameras.txt 中的内参进行修改 (对输入图像全部进行了 resize 操作，因此需要修改相机内参，将fx, fy, cx, cy 都除以2)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "497596e0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"2. 特征匹配与特征提取 \n",
|
||||
"``` bash\n",
|
||||
" colmap feature_extractor \\\n",
|
||||
" --database_path /path/to/project/database.db \\ \n",
|
||||
" --image_path /path/to/project/images\n",
|
||||
"```\n",
|
||||
"``` bash\n",
|
||||
" colmap exhaustive_matcher \\\n",
|
||||
" --database_path /path/to/project/database.db\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "590c5ba8",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"3. 三角化重建 (保存的点云和其他文件均为bin格式)\n",
|
||||
"``` bash\n",
|
||||
" colmap point_triangulator \\\n",
|
||||
" --database_path /path/to/project/database.db \\\n",
|
||||
" --image_path /path/to/project/images \\\n",
|
||||
" --input_path /path/to/sparse_model \\\n",
|
||||
" --output_path /path/to/triangulated_model\n",
|
||||
"\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"查看txt结果\n",
|
||||
"``` bash\n",
|
||||
" colmap model_converter \\\n",
|
||||
" --input_path 0 \\\n",
|
||||
" --output_path 0_txt_from_livo2 \\\n",
|
||||
" --output_type TXT\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6c2b853f",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d359ac68",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"4. 稠密重建(optional)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "77250b4b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# 3.训练"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d44f71f7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# baseline raw gs for training\n",
|
||||
"!CUDA_VISIBLE_DEVICES=1 python train.py \\\n",
|
||||
" -s data/tree_01_livo2 \\\n",
|
||||
" -m data/tree_01_livo2/outputs/3dgs_baseline\n",
|
||||
" \n",
|
||||
"# render\n",
|
||||
"!CUDA_VISIBLE_DEVICES=1 python render.py \\\n",
|
||||
" -s data/tree_01_colmap \\\n",
|
||||
" -m data/tree_01_colmap/outputs/3dgs_baseline "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0156e92d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[[2, 4, 5], [1, 5, 4]]"
|
||||
]
|
||||
},
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"\n",
|
||||
"iss = [[1,5,4],[2,4,5]]\n",
|
||||
"iss.sort(key=lambda x: [x[1],x[0]], reverse=True)\n",
|
||||
"iss"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bf857aee",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"class Solution(object):\n",
|
||||
" def merge(self, intervals):\n",
|
||||
" \"\"\"\n",
|
||||
" :type intervals: List[List[int]]\n",
|
||||
" :rtype: List[List[int]]\n",
|
||||
" \"\"\"\n",
|
||||
" if not intervals:\n",
|
||||
" return []\n",
|
||||
" # 先按区间的起始位置排序\n",
|
||||
" intervals.sort(key=lambda x: x[0])\n",
|
||||
" merged = [intervals[0]]\n",
|
||||
" for i in range(1, len(intervals)):\n",
|
||||
" # 如果当前区间与上一个区间重叠，则合并\n",
|
||||
" if intervals[i][0] <= merged[-1][1]:\n",
|
||||
" merged[-1][1] = max(merged[-1][1], intervals[i][1])\n",
|
||||
" else:\n",
|
||||
" merged.append(intervals[i])\n",
|
||||
" return merged"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@ -583,15 +24,7 @@
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.8.18"
|
||||
}
|
||||
},
|
||||
|
||||
183
xy_utils/tools/images_utils.py
Normal file
183
xy_utils/tools/images_utils.py
Normal file
@ -0,0 +1,183 @@
|
||||
import os
|
||||
from PIL import Image
|
||||
import json
|
||||
import re
|
||||
def get_first_image_info(folder_path):
|
||||
# 检查文件夹是否存在
|
||||
if not os.path.exists(folder_path):
|
||||
print(f"错误：文件夹 '{folder_path}' 不存在")
|
||||
return
|
||||
|
||||
# 获取文件夹中所有文件
|
||||
files = os.listdir(folder_path)
|
||||
|
||||
# 查找第一个图片文件
|
||||
image_extensions = ['.jpg', '.jpeg', '.png', '.bmp', '.gif']
|
||||
image_path = None
|
||||
|
||||
for file in files:
|
||||
file_extension = os.path.splitext(file)[1].lower()
|
||||
if file_extension in image_extensions:
|
||||
image_path = os.path.join(folder_path, file)
|
||||
break
|
||||
|
||||
# 如果没有找到图片文件
|
||||
if image_path is None:
|
||||
print(f"错误：在文件夹 '{folder_path}' 中未找到图片文件")
|
||||
return
|
||||
|
||||
try:
|
||||
# 打开图片并获取信息
|
||||
with Image.open(image_path) as img:
|
||||
width, height = img.size
|
||||
channels = len(img.getbands())
|
||||
|
||||
print(f"找到图片：{os.path.basename(image_path)}")
|
||||
print(f"分辨率：{width} x {height} 像素")
|
||||
print(f"通道数：{channels}")
|
||||
if channels == 1:
|
||||
print("通道说明：单通道（可能是灰度图）")
|
||||
elif channels == 3:
|
||||
print("通道说明：三通道（RGB）")
|
||||
elif channels == 4:
|
||||
print("通道说明：四通道（RGBA，包含Alpha通道）")
|
||||
else:
|
||||
print(f"通道说明：非常规通道数（{channels}通道）")
|
||||
|
||||
except Exception as e:
|
||||
print(f"错误：无法处理图片 '{image_path}' - {str(e)}")
|
||||
|
||||
def generate_depth_params_json(png_folder, output_path):
|
||||
"""
|
||||
遍历指定文件夹中的所有 PNG 图像，提取文件名并生成 depth_params.json 文件。
|
||||
|
||||
参数:
|
||||
- png_folder: PNG 图像所在的文件夹路径
|
||||
- output_path: 生成的 JSON 文件的保存路径
|
||||
"""
|
||||
# 检查 PNG 文件夹是否存在
|
||||
if not os.path.exists(png_folder):
|
||||
print(f"错误：PNG 图像文件夹 '{png_folder}' 不存在")
|
||||
return
|
||||
|
||||
# 获取所有 PNG 文件的文件名（不包含扩展名）
|
||||
png_files = [f for f in os.listdir(png_folder)
|
||||
if os.path.isfile(os.path.join(png_folder, f))
|
||||
and f.lower().endswith('.png')]
|
||||
|
||||
# 提取文件名（不含扩展名）
|
||||
base_names = [os.path.splitext(f)[0] for f in png_files]
|
||||
|
||||
# 如果没有找到 PNG 文件
|
||||
if not base_names:
|
||||
print(f"错误：在文件夹 '{png_folder}' 中未找到 PNG 文件")
|
||||
return
|
||||
|
||||
# 构建 JSON 数据
|
||||
json_data = {}
|
||||
for name in base_names:
|
||||
json_data[name] = {
|
||||
"scale": 0.0,
|
||||
"offset": 0.0
|
||||
}
|
||||
|
||||
# 创建输出文件所在的目录（如果不存在）
|
||||
output_dir = os.path.dirname(output_path)
|
||||
if output_dir and not os.path.exists(output_dir):
|
||||
os.makedirs(output_dir)
|
||||
|
||||
# 写入 JSON 文件
|
||||
try:
|
||||
with open(output_path, 'w', encoding='utf-8') as f:
|
||||
json.dump(json_data, f, indent=2)
|
||||
print(f"成功生成 JSON 文件：{output_path}")
|
||||
print(f"共处理 {len(base_names)} 个 PNG 文件")
|
||||
except Exception as e:
|
||||
print(f"错误：无法写入 JSON 文件 '{output_path}' - {str(e)}")
|
||||
|
||||
def resize_image(input_path, output_path=None,scale=2, quality=100):
|
||||
"""
|
||||
input_path = '/home/qinllgroup/hongxiangyu/git_project/livo2-data-utils/10-Mesh-acc/data/delete/stack_acc_10_2/00142-final.png'
|
||||
output_path = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_save_w_depth/depth_maps_2/00142.png'
|
||||
resize_image(input_path, output_path)
|
||||
|
||||
将图片分辨率缩小1/2
|
||||
|
||||
参数:
|
||||
- input_path: 输入图片路径
|
||||
- output_path: 输出图片路径，默认为在原文件名后加 '_resized'
|
||||
- quality: 输出图片质量，范围0-100，默认为95
|
||||
"""
|
||||
try:
|
||||
# 打开图片
|
||||
with Image.open(input_path) as img:
|
||||
# 获取原始尺寸
|
||||
width, height = img.size
|
||||
|
||||
# 计算新尺寸（缩小1/2）
|
||||
new_width = width // scale
|
||||
new_height = height // scale
|
||||
|
||||
# 使用高质量重采样方法
|
||||
resized_img = img.resize((new_width, new_height), Image.LANCZOS)
|
||||
|
||||
# 如果没有指定输出路径，自动生成
|
||||
if output_path is None:
|
||||
base, ext = os.path.splitext(input_path)
|
||||
output_path = f"{base}_resized{ext}"
|
||||
|
||||
# 保存图片，保持原始格式
|
||||
resized_img.save(output_path, quality=quality)
|
||||
|
||||
print(f"成功将图片从 {width}x{height} 缩小到 {new_width}x{new_height}")
|
||||
print(f"保存路径: {output_path}")
|
||||
|
||||
return output_path
|
||||
|
||||
except Exception as e:
|
||||
print(f"错误: 无法处理图片 {input_path} - {str(e)}")
|
||||
return None
|
||||
|
||||
def batch_rename_files(folder_path):
|
||||
"""
|
||||
批量重命名指定文件夹中的所有文件，移除文件名末尾的 -final
|
||||
|
||||
参数:
|
||||
- folder_path: 要处理的文件夹路径
|
||||
"""
|
||||
# 检查文件夹是否存在
|
||||
if not os.path.exists(folder_path):
|
||||
print(f"错误：文件夹 '{folder_path}' 不存在")
|
||||
return
|
||||
|
||||
# 获取文件夹中的所有文件
|
||||
files = os.listdir(folder_path)
|
||||
|
||||
# 用于匹配 -final 的正则表达式模式
|
||||
pattern = re.compile(r'^(.*?)-final(\.[^.]+)?$')
|
||||
|
||||
renamed_count = 0
|
||||
|
||||
# 遍历所有文件并进行重命名
|
||||
for filename in files:
|
||||
file_path = os.path.join(folder_path, filename)
|
||||
|
||||
# 只处理文件，不处理文件夹
|
||||
if os.path.isfile(file_path):
|
||||
# 使用正则表达式匹配文件名
|
||||
match = pattern.match(filename)
|
||||
|
||||
if match:
|
||||
# 获取新文件名
|
||||
new_name = match.group(1) + (match.group(2) or '')
|
||||
new_path = os.path.join(folder_path, new_name)
|
||||
|
||||
try:
|
||||
# 执行重命名
|
||||
os.rename(file_path, new_path)
|
||||
print(f"已重命名: {filename} -> {new_name}")
|
||||
renamed_count += 1
|
||||
except Exception as e:
|
||||
print(f"错误：无法重命名文件 '{filename}' - {str(e)}")
|
||||
|
||||
print(f"重命名完成！共处理 {renamed_count} 个文件")
|
||||
Loading…
Reference in New Issue
Block a user