Open eternalland opened 2 months ago
ingra14m
commented
2 months ago Hi, thanks for your interest and sorry for the late reply.
From my perspective, I think that you wanna see the rendering results from any viewpoint after training.
You can use python render.py -m your/path/to/model --mode video
eternalland
commented
4 weeks ago Hi, thanks for your interest and sorry for the late reply.
From my perspective, I think that you wanna see the rendering results from any viewpoint after training.
You can use
python render.py -m your/path/to/model --mode video
@ingra14m Thanks very much for your answer. But after I input "python render.py -m ~/postg/thesis/Spec-Gaussian/Spec-Gaussian/outputs/nerf/drums --mode video", it displays this following error. Does this attribute exist in the .ply ?
Looking for config file in /home/mayu/postg/thesis/Spec-Gaussian/Spec-Gaussian/outputs/nerf/drums/cfg_args Config file found: /home/mayu/postg/thesis/Spec-Gaussian/Spec-Gaussian/outputs/nerf/drums/cfg_args Rendering /home/mayu/postg/thesis/Spec-Gaussian/Spec-Gaussian/outputs/nerf/drums Loading trained model at iteration 30000 [29/09 21:58:09] Found transforms_train.json file, assuming Blender data set! [29/09 21:58:09] Reading Training Transforms [29/09 21:58:09] Reading Test Transforms [29/09 21:58:13] Loading Training Cameras [29/09 21:58:21] Loading Test Cameras [29/09 21:58:23] Traceback (most recent call last): File "render.py", line 215, in
args.skip_test, args.mode) File "render.py", line 169, in render_sets scene = Scene(dataset, gaussians, load_iteration=iteration, shuffle=False) File "/home/1/postg/thesis/Spec-Gaussian/Spec-Gaussian/scene/init.py", line 97, in init og_number_points=len(scene_info.point_cloud.points)) File "/home/1/postg/thesis/Spec-Gaussian/Spec-Gaussian/scene/gaussian_model.py", line 211, in load_ply features_dc[:, 0, 0] = np.asarray(plydata.elements[0]["f_dc_0"]) File "/home/1/anaconda3/envs/spec-gaussian-env/lib/python3.7/site-packages/plyfile.py", line 827, in getitem return self.data[key] File "/home/1/anaconda3/envs/spec-gaussian-env/lib/python3.7/site-packages/numpy/core/memmap.py", line 334, in getitem res = super().getitem(index) ValueError: no field of name f_dc_0
I am extremely grateful for your work. Now that running and training these codes has resulted in the generation of rendered images, depth maps, normal maps, and point clouds, could you kindly guide me on how I can further produce a 3D panoramic view? Thank you!