Yihua
Hi, It's normal on self-captured datasets since the resolution is high and the scene is unbounded requiring a lot of Gaussians modeling both the foreground and background. During demo making,...
Hi, Happy to see the discussion. I have updated the sharing link of the old version code: https://pan.baidu.com/s/1Ysa3ehDmeOX5EV6insK4dg?pwd=1234. Hope the code helps as a reference.
Hi, If you strictly follow the readme instructions, the results won't vary too much. The two values are quite close and may differ from machines, seeds, and environments. If you...
Hi, Indeed, the code here: https://github.com/yihua7/SC-GS/blob/26cd57d09598b2f5d951029808a5ac9f0ff4f626/train_gui.py#L1663 is that the program checks for the presence of saved handle points before deciding to render the deformation or not. If your intention is...
Hi, Could you show the frames of your video? The problem should be that your video is hard for camera calibration using COLMAP and only two images are estimated with...
Hi, Sorry for the late reply. You can use the function [readColmapSceneInfo](https://github.com/yihua7/SC-GS/blob/26cd57d09598b2f5d951029808a5ac9f0ff4f626/scene/dataset_readers.py#L201) instead of [readNerfSyntheticInfo](https://github.com/yihua7/SC-GS/blob/26cd57d09598b2f5d951029808a5ac9f0ff4f626/scene/dataset_readers.py#L327). Looking forward to the feedback :)
Hi, I am sorry to hear that. Maybe you can try the solution here: https://github.com/hoffstadt/DearPyGui/issues/2222 I don't have much to offer since I haven't met such an error. Sorry about...
Hi, Thank you for your interest! - We have shown both novel view synthesis and editing cases of HyperNeRF datasets on our [homepage](https://yihua7.github.io/SC-GS-web/). - The arguments can be like `--gt_alpha_mask_as_dynamic_mask...
Hi, There is no need to re-estimate camera poses for the scenes shown on our homepage because their cameras are roughly correct. You can optionally choose to run MiVOS to...
- The dynamic masks make the representation more efficient. Since the prior dynamics are provided, control points and MLP only need to model the dynamics of unmasked regions (with `--gt_alpha_mask_as_dynamic_mask...