Jiazhong Cen
Jiazhong Cen
How did you extract the mask scales of the scene? Seems no scale is available.
Please check [here](https://github.com/Jumpat/SegAnyGAussians/blob/96e5021f2544af95e7705f91ecd8db6bb5cba381/scene/dataset_readers.py#L114). Did the script run readColmapCameras correctly? I doubt that the code use a wrong data loader, maybe a bug.
Yeah. Rendering the results can only get images. In the SAGA GUI, it generate a 0-1 bitmap, which depict the Gaussians belong to the target of interest. The point cloud...
Hi, we use open-clip-torch=2.22.0
> I have met the same problem. I tried open-clip-torch=2.22.0 but it still gets Traceback (most recent call last): File "get_clip_features.py", line 19, in clip_model = load_clip() File "/home/code/SegAnyGAussians-2/clip_utils/clip_utils.py", line...
Hi, this can be achieved through merging all selected object binary masks into one single .pt file.
Hi, sorry for the late response. You need to extract these mask scales by yourself. Please check the **prepare data** section in our README.
You can leave your name and institute and e-mail, to avoid misuse of the dataset. Then, I will send a copy to you.
Hi, I think 10GB might not be sufficient. You could try using a lower resolution for training and sampling fewer scales. That said, I still doubt whether 10GB will be...
Hi, sorry for the late response. I guess there are some problem with the camera poses. You need to align it with the original 3D-GS requirements (I'm not sure the...