gaussian-splatting/utils/camera_utils.py
Matthieu Gendrin 5db5c254f4 Manage central point different from center of image
In some cases, calibration gives central point cx,cy != (0.5,0.5), or it
can be decided to crop the input images.
In those cases, it is necessary to split fovx to fovXleft,fovXright and fovy to fovYtop,fovYbottom

Note that the export of cameras to cameras.json merges those values back
to the basic fovx,fovy. This aims at avoiding the modification of
diff_gaussian_rasterization branch used for SIBR_gaussianViewer_app.

Signed-off-by: Matthieu Gendrin <matthieu.gendrin@orange.com>
2024-03-18 13:26:07 +01:00

84 lines
2.9 KiB
Python

#
# 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
#
from scene.cameras import Camera
import numpy as np
from utils.general_utils import PILtoTorch
from utils.graphics_utils import fov2focal
import math
WARNED = False
def loadCam(args, id, cam_info, resolution_scale):
orig_w, orig_h = cam_info.image.size
if args.resolution in [1, 2, 4, 8]:
resolution = round(orig_w/(resolution_scale * args.resolution)), round(orig_h/(resolution_scale * args.resolution))
else: # should be a type that converts to float
if args.resolution == -1:
if orig_w > 1600:
global WARNED
if not WARNED:
print("[ INFO ] Encountered quite large input images (>1.6K pixels width), rescaling to 1.6K.\n "
"If this is not desired, please explicitly specify '--resolution/-r' as 1")
WARNED = True
global_down = orig_w / 1600
else:
global_down = 1
else:
global_down = orig_w / args.resolution
scale = float(global_down) * float(resolution_scale)
resolution = (int(orig_w / scale), int(orig_h / scale))
resized_image_rgb = PILtoTorch(cam_info.image, resolution)
gt_image = resized_image_rgb[:3, ...]
loaded_mask = None
if resized_image_rgb.shape[1] == 4:
loaded_mask = resized_image_rgb[3:4, ...]
return Camera(colmap_id=cam_info.uid, R=cam_info.R, T=cam_info.T,
FovXleft=cam_info.FovXleft, FovXright=cam_info.FovXright, FovYtop=cam_info.FovYtop, FovYbottom=cam_info.FovYbottom,
image=gt_image, gt_alpha_mask=loaded_mask,
image_name=cam_info.image_name, uid=id, data_device=args.data_device)
def cameraList_from_camInfos(cam_infos, resolution_scale, args):
camera_list = []
for id, c in enumerate(cam_infos):
camera_list.append(loadCam(args, id, c, resolution_scale))
return camera_list
def camera_to_JSON(id, camera : Camera):
Rt = np.zeros((4, 4))
Rt[:3, :3] = camera.R.transpose()
Rt[:3, 3] = camera.T
Rt[3, 3] = 1.0
W2C = np.linalg.inv(Rt)
pos = W2C[:3, 3]
rot = W2C[:3, :3]
serializable_array_2d = [x.tolist() for x in rot]
camera_entry = {
'id' : id,
'img_name' : camera.image_name,
'width' : camera.width,
'height' : camera.height,
'position': pos.tolist(),
'rotation': serializable_array_2d,
'fy' : camera.height / (2 * math.tan((camera.FovYbottom - camera.FovYtop) / 2)),
'fx' : camera.width / (2 * math.tan((camera.FovXright - camera.FovXleft) / 2))
}
return camera_entry