mirror of
https://github.com/graphdeco-inria/gaussian-splatting
synced 2025-06-26 18:18:11 +00:00
created sky and groud box
This commit is contained in:
Xun2001
parent
7c4a7bd800
commit
81590b1f57
@ -40,8 +40,8 @@ class ParamGroup:
|
||||
def extract(self, args):
|
||||
group = GroupParams()
|
||||
for arg in vars(args).items():
|
||||
if arg[0] in vars(self) or ("_" + arg[0]) in vars(self):
|
||||
setattr(group, arg[0], arg[1])
|
||||
if arg[0] in vars(self) or ("_" + arg[0]) in vars(self): # 将args中的参数进行分流，分给不同的Params；所以Param初始化中没有的不能额外加入
|
||||
setattr(group, arg[0], arg[1]) # 内置函数，将属性 arg[0] 和对应的值 arg[1] 赋给group
|
||||
return group
|
||||
|
||||
class ModelParams(ParamGroup):
|
||||
@ -56,7 +56,11 @@ class ModelParams(ParamGroup):
|
||||
self.train_test_exp = False
|
||||
self.data_device = "cuda"
|
||||
self.eval = False
|
||||
super().__init__(parser, "Loading Parameters", sentinel)
|
||||
self.skybox_locked = False
|
||||
self.skybox_num = 0
|
||||
self.scaffold_file = ""
|
||||
self.bounds_file = ""
|
||||
super().__init__(parser, "Loading Parameters", sentinel) # add parameters into parser
|
||||
|
||||
def extract(self, args):
|
||||
g = super().extract(args)
|
||||
|
||||
@ -80,7 +80,13 @@ class Scene:
|
||||
"iteration_" + str(self.loaded_iter),
|
||||
"point_cloud.ply"), args.train_test_exp)
|
||||
else:
|
||||
self.gaussians.create_from_pcd(scene_info.point_cloud, scene_info.train_cameras, self.cameras_extent)
|
||||
self.gaussians.create_from_pcd(scene_info.point_cloud,
|
||||
scene_info.train_cameras,
|
||||
self.cameras_extent,
|
||||
args.skybox_num,
|
||||
args.scaffold_file,
|
||||
args.bounds_file,
|
||||
args.skybox_locked)
|
||||
|
||||
def save(self, iteration):
|
||||
point_cloud_path = os.path.join(self.model_path, "point_cloud/iteration_{}".format(iteration))
|
||||
|
||||
@ -122,7 +122,10 @@ def fetchPly(path):
|
||||
vertices = plydata['vertex']
|
||||
positions = np.vstack([vertices['x'], vertices['y'], vertices['z']]).T
|
||||
colors = np.vstack([vertices['red'], vertices['green'], vertices['blue']]).T / 255.0
|
||||
if 'nx' in vertices and 'ny' in vertices and 'nz' in vertices:
|
||||
normals = np.vstack([vertices['nx'], vertices['ny'], vertices['nz']]).T
|
||||
else:
|
||||
normals = None
|
||||
return BasicPointCloud(points=positions, colors=colors, normals=normals)
|
||||
|
||||
def storePly(path, xyz, rgb):
|
||||
|
||||
@ -21,6 +21,7 @@ from utils.sh_utils import RGB2SH
|
||||
from simple_knn._C import distCUDA2
|
||||
from utils.graphics_utils import BasicPointCloud
|
||||
from utils.general_utils import strip_symmetric, build_scaling_rotation
|
||||
from scene.xy_utils import storePly
|
||||
|
||||
try:
|
||||
from diff_gaussian_rasterization import SparseGaussianAdam
|
||||
@ -65,6 +66,9 @@ class GaussianModel:
|
||||
self.spatial_lr_scale = 0
|
||||
self.setup_functions()
|
||||
|
||||
self.skybox_points = 0
|
||||
self.skybox_locked = True
|
||||
|
||||
def capture(self):
|
||||
return (
|
||||
self.active_sh_degree,
|
||||
@ -146,34 +150,137 @@ class GaussianModel:
|
||||
if self.active_sh_degree < self.max_sh_degree:
|
||||
self.active_sh_degree += 1
|
||||
|
||||
def create_from_pcd(self, pcd : BasicPointCloud, cam_infos : int, spatial_lr_scale : float):
|
||||
def create_from_pcd(self,
|
||||
pcd : BasicPointCloud,
|
||||
cam_infos : int,
|
||||
spatial_lr_scale : float,
|
||||
addition_points: int,
|
||||
scaffold_file: str,
|
||||
bounds_file: str,
|
||||
skybox_locked: bool):
|
||||
|
||||
# if addition_points > 0:
|
||||
# self.skybox_points = addition_points # 原主代码中控制 skybox_points 更新的逻辑
|
||||
# groundbox_points = addition_points // 2
|
||||
# skybox_points = addition_points - groundbox_points
|
||||
|
||||
self.skybox_points = addition_points
|
||||
skybox_points = addition_points
|
||||
self.skybox_locked = skybox_locked
|
||||
self.spatial_lr_scale = spatial_lr_scale
|
||||
fused_point_cloud = torch.tensor(np.asarray(pcd.points)).float().cuda()
|
||||
fused_color = RGB2SH(torch.tensor(np.asarray(pcd.colors)).float().cuda())
|
||||
|
||||
xyz_np = np.asarray(pcd.points)
|
||||
xyz = torch.tensor(xyz_np).float().cuda() # [N,3] use xyz replace fused_point_cloud
|
||||
fused_color = torch.tensor(np.asarray(pcd.colors)).float().cuda() # [N,3] from 0 to 1
|
||||
|
||||
# segment ground plane
|
||||
from utils.points_utils import fit_ground_plane
|
||||
plane_model, inliers = fit_ground_plane(xyz_np, threshold=0.001)
|
||||
inliers = np.array(inliers)
|
||||
ground_points = xyz_np[inliers]
|
||||
ground_center = ground_points.mean(axis=0)
|
||||
ground_radius = np.linalg.norm(ground_points - ground_center, axis=1).max() # need-check
|
||||
|
||||
if scaffold_file != "" and skybox_points > 0: # TODO: load scaffold_file
|
||||
print(f"Overriding skybox_points: loading skybox from scaffold_file: {scaffold_file}")
|
||||
skybox_points = 0
|
||||
|
||||
if skybox_points > 0:
|
||||
radius = ground_radius
|
||||
mean = torch.tensor(ground_center).float().cuda()
|
||||
theta = (2.0 * torch.pi * torch.rand(skybox_points, device="cuda")).float() # torch.rand generate [0,1)
|
||||
phi = (torch.arccos(1.0 - 1.4 * torch.rand(skybox_points, device="cuda"))).float() # arc cos [-0.4,1] --> 角度 [0,110]
|
||||
skybox_xyz = torch.zeros((skybox_points, 3))
|
||||
skybox_xyz[:, 0] = radius * 5 * torch.cos(theta)*torch.sin(phi) # 5 * radius
|
||||
skybox_xyz[:, 1] = radius * 5 * torch.sin(theta)*torch.sin(phi)
|
||||
skybox_xyz[:, 2] = radius * 5 * torch.cos(phi)
|
||||
|
||||
normal = torch.tensor(plane_model[:3], dtype=torch.float32)
|
||||
up = torch.tensor([0.0, 0.0, 1.0])
|
||||
|
||||
from utils.points_utils import create_rotation_matrix
|
||||
R = create_rotation_matrix(up, normal)
|
||||
R = torch.from_numpy(R).float()
|
||||
skybox_xyz = (R@skybox_xyz.T).T
|
||||
|
||||
skybox_xyz += mean.cpu() # put points in the center of the scene
|
||||
xyz = torch.concat((skybox_xyz.cuda(), xyz))
|
||||
fused_color = torch.concat((torch.ones((skybox_points, 3)).cuda(), fused_color))
|
||||
fused_color[:skybox_points,0] *= 0.7
|
||||
fused_color[:skybox_points,1] *= 0.8
|
||||
fused_color[:skybox_points,2] *= 0.95
|
||||
|
||||
groundbox_points = 0
|
||||
if groundbox_points > 0:
|
||||
radius = ground_radius
|
||||
mean = torch.tensor(ground_center).float().cuda()
|
||||
|
||||
a, b, c, d = plane_model
|
||||
theta = 2.0 * torch.pi * torch.rand(groundbox_points, device="cuda") # 角度 [0, 2pi)
|
||||
r = radius * torch.sqrt(torch.rand(groundbox_points, device="cuda")) # 半径范围 [0, 2*radius]
|
||||
|
||||
groundbox_xyz = torch.zeros((groundbox_points, 3))
|
||||
groundbox_xyz[:, 0] = r * torch.cos(theta)
|
||||
groundbox_xyz[:, 1] = r * torch.sin(theta)
|
||||
groundbox_xyz[:, 2] = (-a * groundbox_xyz[:, 0] - b * groundbox_xyz[:, 1] - d) / c
|
||||
groundbox_xyz += mean.cpu()
|
||||
groundbox_color = torch.ones((groundbox_points, 3), device="cuda") * torch.tensor([0.5, 0.5, 0.5], device="cuda")
|
||||
|
||||
xyz = torch.concat((groundbox_xyz.cuda(), xyz), dim=0)
|
||||
fused_color = torch.concat((groundbox_color.cuda(), fused_color), dim=0)
|
||||
|
||||
debug_xy = True
|
||||
if debug_xy:
|
||||
folder = "/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_debug/mini3/outputs_debug"
|
||||
sky_ply_path = os.path.join(folder, "skybox_scene_init.ply")
|
||||
storePly(sky_ply_path, xyz.cpu(), fused_color.cpu()*255)
|
||||
print("save sky and groud init ply in: ", sky_ply_path)
|
||||
|
||||
|
||||
# fused_point_cloud = torch.tensor(np.asarray(pcd.points)).float().cuda()
|
||||
|
||||
# fused_color = RGB2SH(torch.tensor(np.asarray(pcd.colors)).float().cuda())
|
||||
features = torch.zeros((fused_color.shape[0], 3, (self.max_sh_degree + 1) ** 2)).float().cuda()
|
||||
features[:, :3, 0 ] = fused_color
|
||||
features[:, :3, 0 ] = RGB2SH(fused_color)
|
||||
features[:, 3:, 1:] = 0.0
|
||||
|
||||
print("Number of points at initialisation : ", fused_point_cloud.shape[0])
|
||||
# dist2 = torch.clamp_min(distCUDA2(torch.from_numpy(np.asarray(pcd.points)).float().cuda()), 0.0000001)
|
||||
dist2 = torch.clamp_min(distCUDA2(xyz), 0.0000001) # shape [],to caculate the
|
||||
if scaffold_file == "" and skybox_points > 0:
|
||||
dist2[:skybox_points] *= 10 # sky points * 10 扩大每个高斯最近
|
||||
dist2[skybox_points:] = torch.clamp_max(dist2[skybox_points:], 10) # 使得场景内高斯点的距离小于10
|
||||
|
||||
dist2 = torch.clamp_min(distCUDA2(torch.from_numpy(np.asarray(pcd.points)).float().cuda()), 0.0000001)
|
||||
scales = torch.log(torch.sqrt(dist2))[...,None].repeat(1, 3)
|
||||
rots = torch.zeros((fused_point_cloud.shape[0], 4), device="cuda")
|
||||
rots = torch.zeros((xyz.shape[0], 4), device="cuda")
|
||||
rots[:, 0] = 1
|
||||
|
||||
opacities = self.inverse_opacity_activation(0.1 * torch.ones((fused_point_cloud.shape[0], 1), dtype=torch.float, device="cuda"))
|
||||
# opacities = self.inverse_opacity_activation(0.1 * torch.ones((fused_point_cloud.shape[0], 1), dtype=torch.float, device="cuda"))
|
||||
if scaffold_file == "" and skybox_points > 0:
|
||||
opacities = self.inverse_opacity_activation(0.02 * torch.ones((xyz.shape[0], 1), dtype=torch.float, device="cuda"))
|
||||
opacities[:skybox_points] = 0.7 # sky 0.02 other 0.7
|
||||
else:
|
||||
opacities = self.inverse_opacity_activation(0.01 * torch.ones((xyz.shape[0], 1), dtype=torch.float, device="cuda"))
|
||||
|
||||
self._xyz = nn.Parameter(fused_point_cloud.requires_grad_(True))
|
||||
self._features_dc = nn.Parameter(features[:,:,0:1].transpose(1, 2).contiguous().requires_grad_(True))
|
||||
self._features_rest = nn.Parameter(features[:,:,1:].transpose(1, 2).contiguous().requires_grad_(True))
|
||||
features_dc = features[:,:,0:1].transpose(1, 2).contiguous()
|
||||
features_rest = features[:,:,1:].transpose(1, 2).contiguous()
|
||||
self.scaffold_points = None
|
||||
if scaffold_file != "":
|
||||
print("TODO:load scaffold_file")
|
||||
|
||||
self._xyz = nn.Parameter(xyz.requires_grad_(True))
|
||||
self._features_dc = nn.Parameter(features_dc.requires_grad_(True))
|
||||
self._features_rest = nn.Parameter(features_rest.requires_grad_(True))
|
||||
self._scaling = nn.Parameter(scales.requires_grad_(True))
|
||||
self._rotation = nn.Parameter(rots.requires_grad_(True))
|
||||
self._opacity = nn.Parameter(opacities.requires_grad_(True))
|
||||
self.max_radii2D = torch.zeros((self.get_xyz.shape[0]), device="cuda")
|
||||
|
||||
self.exposure_mapping = {cam_info.image_name: idx for idx, cam_info in enumerate(cam_infos)}
|
||||
|
||||
self.pretrained_exposures = None
|
||||
exposure = torch.eye(3, 4, device="cuda")[None].repeat(len(cam_infos), 1, 1)
|
||||
self._exposure = nn.Parameter(exposure.requires_grad_(True))
|
||||
print("Number of points at initialisation : ", self._xyz.shape[0])
|
||||
|
||||
def training_setup(self, training_args):
|
||||
self.percent_dense = training_args.percent_dense
|
||||
|
||||
21
scene/xy_utils.py
Normal file
21
scene/xy_utils.py
Normal file
@ -0,0 +1,21 @@
|
||||
from plyfile import PlyData, PlyElement
|
||||
import numpy as np
|
||||
|
||||
|
||||
def storePly(path, xyz, rgb):
|
||||
# Define the dtype for the structured array
|
||||
# RGB should be 0-255
|
||||
dtype = [('x', 'f4'), ('y', 'f4'), ('z', 'f4'),
|
||||
('nx', 'f4'), ('ny', 'f4'), ('nz', 'f4'),
|
||||
('red', 'u1'), ('green', 'u1'), ('blue', 'u1')]
|
||||
|
||||
normals = np.zeros_like(xyz)
|
||||
|
||||
elements = np.empty(xyz.shape[0], dtype=dtype)
|
||||
attributes = np.concatenate((xyz, normals, rgb), axis=1)
|
||||
elements[:] = list(map(tuple, attributes))
|
||||
|
||||
# Create the PlyData object and write to file
|
||||
vertex_element = PlyElement.describe(elements, 'vertex')
|
||||
ply_data = PlyData([vertex_element])
|
||||
ply_data.write(path)
|
||||
@ -1 +1 @@
|
||||
Subproject commit 9c5c2028f6fbee2be239bc4c9421ff894fe4fbe0
|
||||
Subproject commit 26ce026ae9d3cfa56a103279b863a9f320c3e555
|
||||
307
train-sky.py
Normal file
307
train-sky.py
Normal file
@ -0,0 +1,307 @@
|
||||
#
|
||||
# Copyright (C) 2023, Inria
|
||||
# GRAPHDECO research group, https://team.inria.fr/graphdeco
|
||||
# All rights reserved.
|
||||
#
|
||||
# This software is free for non-commercial, research and evaluation use
|
||||
# under the terms of the LICENSE.md file.
|
||||
#
|
||||
# For inquiries contact george.drettakis@inria.fr
|
||||
#
|
||||
|
||||
# edit like train_coarse.py
|
||||
|
||||
import os
|
||||
import torch
|
||||
from random import randint
|
||||
from utils.loss_utils import l1_loss, ssim
|
||||
from gaussian_renderer import render, network_gui
|
||||
import sys
|
||||
from scene import Scene, GaussianModel
|
||||
from utils.general_utils import safe_state, get_expon_lr_func
|
||||
import uuid
|
||||
from tqdm import tqdm
|
||||
from utils.image_utils import psnr
|
||||
from argparse import ArgumentParser, Namespace
|
||||
from arguments import ModelParams, PipelineParams, OptimizationParams
|
||||
try:
|
||||
from torch.utils.tensorboard import SummaryWriter
|
||||
TENSORBOARD_FOUND = True
|
||||
except ImportError:
|
||||
TENSORBOARD_FOUND = False
|
||||
|
||||
try:
|
||||
from fused_ssim import fused_ssim
|
||||
FUSED_SSIM_AVAILABLE = True
|
||||
except:
|
||||
FUSED_SSIM_AVAILABLE = False
|
||||
|
||||
try:
|
||||
from diff_gaussian_rasterization import SparseGaussianAdam
|
||||
SPARSE_ADAM_AVAILABLE = True
|
||||
except:
|
||||
SPARSE_ADAM_AVAILABLE = False
|
||||
|
||||
def training(dataset, opt, pipe, testing_iterations, saving_iterations, checkpoint_iterations, checkpoint, debug_from):
|
||||
# dataset = args
|
||||
if not SPARSE_ADAM_AVAILABLE and opt.optimizer_type == "sparse_adam":
|
||||
sys.exit(f"Trying to use sparse adam but it is not installed, please install the correct rasterizer using pip install [3dgs_accel].")
|
||||
|
||||
first_iter = 0
|
||||
tb_writer = prepare_output_and_logger(dataset)
|
||||
gaussians = GaussianModel(dataset.sh_degree, opt.optimizer_type)
|
||||
print(f"dataset.sh_degree: {dataset.sh_degree}")
|
||||
scene = Scene(dataset, gaussians)
|
||||
debug_xy = True
|
||||
if debug_xy:
|
||||
scene.save(0)
|
||||
gaussians.training_setup(opt)
|
||||
if checkpoint:
|
||||
(model_params, first_iter) = torch.load(checkpoint)
|
||||
gaussians.restore(model_params, opt)
|
||||
|
||||
bg_color = [1, 1, 1] if dataset.white_background else [0, 0, 0]
|
||||
background = torch.tensor(bg_color, dtype=torch.float32, device="cuda")
|
||||
|
||||
iter_start = torch.cuda.Event(enable_timing = True)
|
||||
iter_end = torch.cuda.Event(enable_timing = True)
|
||||
|
||||
use_sparse_adam = opt.optimizer_type == "sparse_adam" and SPARSE_ADAM_AVAILABLE
|
||||
depth_l1_weight = get_expon_lr_func(opt.depth_l1_weight_init, opt.depth_l1_weight_final, max_steps=opt.iterations)
|
||||
|
||||
viewpoint_stack = scene.getTrainCameras().copy()
|
||||
viewpoint_indices = list(range(len(viewpoint_stack)))
|
||||
ema_loss_for_log = 0.0
|
||||
ema_Ll1depth_for_log = 0.0
|
||||
|
||||
progress_bar = tqdm(range(first_iter, opt.iterations), desc="Training progress")
|
||||
first_iter += 1
|
||||
|
||||
# freeze xyz
|
||||
for param_group in gaussians.optimizer.param_groups: # xyz,f_dc,f_rest,opacity,scaling,rotation
|
||||
if param_group["name"] == "xyz":
|
||||
param_group['lr'] = 0.0
|
||||
|
||||
for iteration in range(first_iter, opt.iterations + 1):
|
||||
if network_gui.conn == None:
|
||||
network_gui.try_connect()
|
||||
while network_gui.conn != None:
|
||||
try:
|
||||
net_image_bytes = None
|
||||
custom_cam, do_training, pipe.convert_SHs_python, pipe.compute_cov3D_python, keep_alive, scaling_modifer = network_gui.receive()
|
||||
if custom_cam != None:
|
||||
net_image = render(custom_cam, gaussians, pipe, background, scaling_modifier=scaling_modifer, use_trained_exp=dataset.train_test_exp, separate_sh=SPARSE_ADAM_AVAILABLE)["render"]
|
||||
net_image_bytes = memoryview((torch.clamp(net_image, min=0, max=1.0) * 255).byte().permute(1, 2, 0).contiguous().cpu().numpy())
|
||||
network_gui.send(net_image_bytes, dataset.source_path)
|
||||
if do_training and ((iteration < int(opt.iterations)) or not keep_alive):
|
||||
break
|
||||
except Exception as e:
|
||||
network_gui.conn = None
|
||||
|
||||
iter_start.record()
|
||||
|
||||
gaussians.update_learning_rate(iteration)
|
||||
|
||||
# Every 1000 its we increase the levels of SH up to a maximum degree
|
||||
if iteration % 1000 == 0:
|
||||
gaussians.oneupSHdegree()
|
||||
|
||||
# Pick a random Camera
|
||||
if not viewpoint_stack:
|
||||
viewpoint_stack = scene.getTrainCameras().copy()
|
||||
viewpoint_indices = list(range(len(viewpoint_stack)))
|
||||
rand_idx = randint(0, len(viewpoint_indices) - 1)
|
||||
viewpoint_cam = viewpoint_stack.pop(rand_idx)
|
||||
vind = viewpoint_indices.pop(rand_idx)
|
||||
|
||||
# Render
|
||||
if (iteration - 1) == debug_from:
|
||||
pipe.debug = True
|
||||
|
||||
bg = torch.rand((3), device="cuda") if opt.random_background else background
|
||||
|
||||
render_pkg = render(viewpoint_cam, gaussians, pipe, bg, use_trained_exp=dataset.train_test_exp, separate_sh=SPARSE_ADAM_AVAILABLE)
|
||||
image, viewspace_point_tensor, visibility_filter, radii = render_pkg["render"], render_pkg["viewspace_points"], render_pkg["visibility_filter"], render_pkg["radii"]
|
||||
|
||||
if viewpoint_cam.alpha_mask is not None:
|
||||
alpha_mask = viewpoint_cam.alpha_mask.cuda()# can set to sky mask
|
||||
image *= alpha_mask
|
||||
|
||||
# Loss
|
||||
gt_image = viewpoint_cam.original_image.cuda()
|
||||
Ll1 = l1_loss(image, gt_image)
|
||||
if FUSED_SSIM_AVAILABLE:
|
||||
ssim_value = fused_ssim(image.unsqueeze(0), gt_image.unsqueeze(0))
|
||||
else:
|
||||
ssim_value = ssim(image, gt_image)
|
||||
|
||||
loss = (1.0 - opt.lambda_dssim) * Ll1 + opt.lambda_dssim * (1.0 - ssim_value)
|
||||
|
||||
# Depth regularization
|
||||
Ll1depth_pure = 0.0
|
||||
if depth_l1_weight(iteration) > 0 and viewpoint_cam.depth_reliable:
|
||||
invDepth = render_pkg["depth"]
|
||||
mono_invdepth = viewpoint_cam.invdepthmap.cuda()
|
||||
depth_mask = viewpoint_cam.depth_mask.cuda()
|
||||
|
||||
Ll1depth_pure = torch.abs((invDepth - mono_invdepth) * depth_mask).mean()
|
||||
Ll1depth = depth_l1_weight(iteration) * Ll1depth_pure
|
||||
loss += Ll1depth
|
||||
Ll1depth = Ll1depth.item()
|
||||
else:
|
||||
Ll1depth = 0
|
||||
|
||||
loss.backward()
|
||||
|
||||
iter_end.record()
|
||||
|
||||
with torch.no_grad():
|
||||
# Progress bar
|
||||
ema_loss_for_log = 0.4 * loss.item() + 0.6 * ema_loss_for_log
|
||||
ema_Ll1depth_for_log = 0.4 * Ll1depth + 0.6 * ema_Ll1depth_for_log
|
||||
|
||||
if iteration % 10 == 0:
|
||||
progress_bar.set_postfix({"Loss": f"{ema_loss_for_log:.{7}f}", "Depth Loss": f"{ema_Ll1depth_for_log:.{7}f}"})
|
||||
progress_bar.update(10)
|
||||
if iteration == opt.iterations:
|
||||
progress_bar.close()
|
||||
|
||||
# Log and save
|
||||
training_report(tb_writer, iteration, Ll1, loss, l1_loss, iter_start.elapsed_time(iter_end), testing_iterations, scene, render, (pipe, background, 1., SPARSE_ADAM_AVAILABLE, None, dataset.train_test_exp), dataset.train_test_exp)
|
||||
if (iteration in saving_iterations):
|
||||
print("\n[ITER {}] Saving Gaussians".format(iteration))
|
||||
scene.save(iteration)
|
||||
|
||||
# # Densification
|
||||
# if iteration < opt.densify_until_iter:
|
||||
# # Keep track of max radii in image-space for pruning
|
||||
# gaussians.max_radii2D[visibility_filter] = torch.max(gaussians.max_radii2D[visibility_filter], radii[visibility_filter])
|
||||
# gaussians.add_densification_stats(viewspace_point_tensor, visibility_filter)
|
||||
|
||||
# if iteration > opt.densify_from_iter and iteration % opt.densification_interval == 0:
|
||||
# size_threshold = 20 if iteration > opt.opacity_reset_interval else None
|
||||
# gaussians.densify_and_prune(opt.densify_grad_threshold, 0.005, scene.cameras_extent, size_threshold, radii)
|
||||
|
||||
# if iteration % opt.opacity_reset_interval == 0 or (dataset.white_background and iteration == opt.densify_from_iter):
|
||||
# gaussians.reset_opacity()
|
||||
|
||||
# Optimizer step
|
||||
if iteration < opt.iterations:
|
||||
gaussians.exposure_optimizer.step() #
|
||||
gaussians.exposure_optimizer.zero_grad(set_to_none = True)
|
||||
if use_sparse_adam:
|
||||
# # raw 3dgs with sparse adam
|
||||
# visible = radii > 0
|
||||
# gaussians.optimizer.step(visible, radii.shape[0])
|
||||
# gaussians.optimizer.zero_grad(set_to_none = True)
|
||||
gaussians._scaling.grad[:gaussians.skybox_points,:] = 0 # sky points' gradients set to zero
|
||||
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")
|
||||
|
||||
with torch.no_grad():
|
||||
vals, _ = gaussians.get_scaling.max(dim=1) # max scaling for each point
|
||||
violators = vals > scene.cameras_extent * 0.1 # 违反者(过大的点)
|
||||
violators[:gaussians.skybox_points] = False # sky points not considered
|
||||
gaussians._scaling[violators] = gaussians.scaling_inverse_activation(gaussians.get_scaling[violators] * 0.8) # scale down violators
|
||||
|
||||
def prepare_output_and_logger(args):
|
||||
if not args.model_path:
|
||||
if os.getenv('OAR_JOB_ID'):
|
||||
unique_str=os.getenv('OAR_JOB_ID')
|
||||
else:
|
||||
unique_str = str(uuid.uuid4())
|
||||
args.model_path = os.path.join("./output/", unique_str[0:10])
|
||||
|
||||
# Set up output folder
|
||||
print("Output folder: {}".format(args.model_path))
|
||||
os.makedirs(args.model_path, exist_ok = True)
|
||||
with open(os.path.join(args.model_path, "cfg_args"), 'w') as cfg_log_f:
|
||||
cfg_log_f.write(str(Namespace(**vars(args))))
|
||||
|
||||
# Create Tensorboard writer
|
||||
tb_writer = None
|
||||
if TENSORBOARD_FOUND:
|
||||
tb_writer = SummaryWriter(args.model_path)
|
||||
else:
|
||||
print("Tensorboard not available: not logging progress")
|
||||
return tb_writer
|
||||
|
||||
def training_report(tb_writer, iteration, Ll1, loss, l1_loss, elapsed, testing_iterations, scene : Scene, renderFunc, renderArgs, train_test_exp):
|
||||
if tb_writer:
|
||||
tb_writer.add_scalar('train_loss_patches/l1_loss', Ll1.item(), iteration)
|
||||
tb_writer.add_scalar('train_loss_patches/total_loss', loss.item(), iteration)
|
||||
tb_writer.add_scalar('iter_time', elapsed, iteration)
|
||||
|
||||
# Report test and samples of training set
|
||||
if iteration in testing_iterations:
|
||||
torch.cuda.empty_cache()
|
||||
validation_configs = ({'name': 'test', 'cameras' : scene.getTestCameras()},
|
||||
{'name': 'train', 'cameras' : [scene.getTrainCameras()[idx % len(scene.getTrainCameras())] for idx in range(5, 30, 5)]})
|
||||
|
||||
for config in validation_configs:
|
||||
if config['cameras'] and len(config['cameras']) > 0:
|
||||
l1_test = 0.0
|
||||
psnr_test = 0.0
|
||||
for idx, viewpoint in enumerate(config['cameras']):
|
||||
image = torch.clamp(renderFunc(viewpoint, scene.gaussians, *renderArgs)["render"], 0.0, 1.0)
|
||||
gt_image = torch.clamp(viewpoint.original_image.to("cuda"), 0.0, 1.0)
|
||||
if train_test_exp:
|
||||
image = image[..., image.shape[-1] // 2:]
|
||||
gt_image = gt_image[..., gt_image.shape[-1] // 2:]
|
||||
if tb_writer and (idx < 5):
|
||||
tb_writer.add_images(config['name'] + "_view_{}/render".format(viewpoint.image_name), image[None], global_step=iteration)
|
||||
if iteration == testing_iterations[0]:
|
||||
tb_writer.add_images(config['name'] + "_view_{}/ground_truth".format(viewpoint.image_name), gt_image[None], global_step=iteration)
|
||||
l1_test += l1_loss(image, gt_image).mean().double()
|
||||
psnr_test += psnr(image, gt_image).mean().double()
|
||||
psnr_test /= len(config['cameras'])
|
||||
l1_test /= len(config['cameras'])
|
||||
print("\n[ITER {}] Evaluating {}: L1 {} PSNR {}".format(iteration, config['name'], l1_test, psnr_test))
|
||||
if tb_writer:
|
||||
tb_writer.add_scalar(config['name'] + '/loss_viewpoint - l1_loss', l1_test, iteration)
|
||||
tb_writer.add_scalar(config['name'] + '/loss_viewpoint - psnr', psnr_test, iteration)
|
||||
|
||||
if tb_writer:
|
||||
tb_writer.add_histogram("scene/opacity_histogram", scene.gaussians.get_opacity, iteration)
|
||||
tb_writer.add_scalar('total_points', scene.gaussians.get_xyz.shape[0], iteration)
|
||||
torch.cuda.empty_cache()
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Set up command line argument parser
|
||||
parser = ArgumentParser(description="Training script parameters")
|
||||
lp = ModelParams(parser)
|
||||
op = OptimizationParams(parser)
|
||||
pp = PipelineParams(parser)
|
||||
parser.add_argument('--ip', type=str, default="127.0.0.1")
|
||||
parser.add_argument('--port', type=int, default=6009)
|
||||
parser.add_argument('--debug_from', type=int, default=-1)
|
||||
parser.add_argument('--detect_anomaly', action='store_true', default=False)
|
||||
parser.add_argument("--test_iterations", nargs="+", type=int, default=[7_000, 10_000, 15_000, 20_000, 25_000, 30_000, 50_000])
|
||||
parser.add_argument("--save_iterations", nargs="+", type=int, default=[7_000, 10_000, 15_000, 20_000, 25_000, 30_000, 50_000])
|
||||
parser.add_argument("--quiet", action="store_true")
|
||||
parser.add_argument('--disable_viewer', action='store_true', default=False)
|
||||
parser.add_argument("--checkpoint_iterations", nargs="+", type=int, default=[])
|
||||
parser.add_argument("--start_checkpoint", type=str, default = None)
|
||||
|
||||
args = parser.parse_args(sys.argv[1:])
|
||||
|
||||
args.save_iterations.append(args.iterations)
|
||||
|
||||
print("Optimizing " + args.model_path)
|
||||
|
||||
# Initialize system state (RNG)
|
||||
safe_state(args.quiet)
|
||||
|
||||
# Start GUI server, configure and run training
|
||||
if not args.disable_viewer:
|
||||
network_gui.init(args.ip, args.port)
|
||||
torch.autograd.set_detect_anomaly(args.detect_anomaly)
|
||||
training(lp.extract(args), op.extract(args), pp.extract(args), args.test_iterations, args.save_iterations, args.checkpoint_iterations, args.start_checkpoint, args.debug_from)
|
||||
|
||||
# All done
|
||||
print("\nTraining complete.")
|
||||
31
utils/points_utils.py
Normal file
31
utils/points_utils.py
Normal file
@ -0,0 +1,31 @@
|
||||
import open3d as o3d
|
||||
import torch
|
||||
def fit_ground_plane(xyz, threshold=0.02):
|
||||
pcd = o3d.geometry.PointCloud()
|
||||
pcd.points = o3d.utility.Vector3dVector(xyz)
|
||||
plane_model, inliers = pcd.segment_plane(distance_threshold=threshold,
|
||||
ransac_n=3,
|
||||
num_iterations=10000)
|
||||
return plane_model, inliers
|
||||
|
||||
def create_rotation_matrix(source_dir, target_dir):
|
||||
|
||||
source_dir = source_dir / torch.norm(source_dir)
|
||||
target_dir = target_dir / torch.norm(target_dir)
|
||||
|
||||
axis = torch.cross(source_dir, target_dir)
|
||||
cos_angle = torch.dot(source_dir, target_dir)
|
||||
|
||||
if torch.norm(axis) < 1e-6:
|
||||
return torch.eye(3, device=source_dir.device)
|
||||
|
||||
axis = axis / torch.norm(axis)
|
||||
# k = axis.unsqueeze(-1)
|
||||
# K = torch.zeros((3, 3), device=source_dir.device)
|
||||
# K[0, 1] = -k[2]
|
||||
# K[0, 2] = k[1]
|
||||
# K[1, 2] = -k[0]
|
||||
# K = K - K.T
|
||||
# R = torch.eye(3, device=source_dir.device) + K + K @ K * (1 - cos_angle) / (1 + cos_angle)
|
||||
R_align = o3d.geometry.get_rotation_matrix_from_axis_angle(axis * torch.acos(cos_angle))
|
||||
return R_align
|
||||
@ -207,7 +207,7 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 2,
|
||||
"id": "56f5cba7",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
@ -215,9 +215,9 @@
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"raw points len : 15254842\n",
|
||||
"downsample points len : 201667\n",
|
||||
"降采样后的点云已保存到 /home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/sparse/0/points3D_filter_0.2.ply，体素大小：0.2\n"
|
||||
"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"
|
||||
]
|
||||
}
|
||||
],
|
||||
@ -225,12 +225,12 @@
|
||||
"import os\n",
|
||||
"from tools.points_utils import voxel_downsample_and_save\n",
|
||||
"\n",
|
||||
"voxel_size = 0.2\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_livo2/sparse/0/points3D_filter.ply'\n",
|
||||
"output_ply_path = f'/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/sparse/0/points3D_filter_{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"
|
||||
]
|
||||
@ -238,26 +238,34 @@
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d1df326d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "8544bb3e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"True"
|
||||
"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"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"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_livo2/livo2_results/pcd/all_raw_points.pcd'\n",
|
||||
"ply_file = '/home/qinllgroup/hongxiangyu/git_project/gaussian-splatting-xy/data/tree_01_livo2/livo2_results/pcd/all_raw_points.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"
|
||||
]
|
||||
@ -515,6 +523,57 @@
|
||||
" -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": {
|
||||
|
||||
19
xy_utils/sky_groud.py
Normal file
19
xy_utils/sky_groud.py
Normal file
@ -0,0 +1,19 @@
|
||||
from tools.points_utils import *
|
||||
import numpy as np
|
||||
import math
|
||||
import open3d as o3d
|
||||
|
||||
|
||||
def fit_ground_plane(xyz, threshold=0.02):
|
||||
"""
|
||||
使用 RANSAC 拟合地面平面模型。
|
||||
返回：平面模型 [a, b, c, d] 和内点索引。
|
||||
"""
|
||||
pcd = o3d.geometry.PointCloud()
|
||||
pcd.points = o3d.utility.Vector3dVector(xyz)
|
||||
plane_model, inliers = pcd.segment_plane(distance_threshold=threshold,
|
||||
ransac_n=3,
|
||||
num_iterations=1000)
|
||||
[a, b, c, d] = plane_model
|
||||
print(f"拟合的地面平面方程: {a:.4f}x + {b:.4f}y + {c:.4f}z + {d:.4f} = 0")
|
||||
return plane_model, inliers
|
||||
@ -56,3 +56,28 @@ def voxel_downsample_and_save(voxel_size, input_ply_path, output_ply_path):
|
||||
# 保存降采样后的点云
|
||||
o3d.io.write_point_cloud(output_ply_path, pcd_downsampled)
|
||||
print(f"降采样后的点云已保存到 {output_ply_path}，体素大小：{voxel_size}")
|
||||
|
||||
def load_pcd(pcd_file_path):
|
||||
pcd = o3d.io.read_point_cloud(pcd_file_path)
|
||||
xyz = np.asarray(pcd.points)
|
||||
rgb = np.asarray(pcd.colors)
|
||||
if np.max(rgb) <= 1.0:
|
||||
rgb = (rgb * 255).astype(np.uint8)
|
||||
return xyz, rgb
|
||||
|
||||
def load_ply(ply_file_path):
|
||||
pcd = o3d.io.read_point_cloud(ply_file_path)
|
||||
xyz = np.asarray(pcd.points)
|
||||
rgb = np.asarray(pcd.colors)
|
||||
if np.max(rgb) <= 1.0:
|
||||
rgb = (rgb * 255).astype(np.uint8)
|
||||
return xyz, rgb
|
||||
|
||||
def save_ply(xyz, colors, file_path):
|
||||
|
||||
pcd = o3d.geometry.PointCloud()
|
||||
pcd.points = o3d.utility.Vector3dVector(xyz)
|
||||
pcd.colors = o3d.utility.Vector3dVector(colors)
|
||||
o3d.io.write_point_cloud(file_path, pcd)
|
||||
|
||||
print(f"保存点云到 {file_path}")
|
||||
Loading…
Reference in New Issue
Block a user