poor result on redwood data

Hi,

Thanks for your great work. I tried to test it on the RedWood bedroom dataset (http://redwood-data.org/indoor_lidar_rgbd/index.html) with downsampled RGB-D images (from 21930 to 219 frames, resolution 640x480), both original and downsampled pointcloud (~5M, 100k points) but cannot get reasonable outputs. After filtering it seems that only the first frame result is remained as I checked the camera pose by reprojecting the first frame depth into the scene scan point cloud. It says originally with 580 prompts in 3d proposal stage and 51 remains after 2d-guided filter. Then 15 after prompt consolidation.

There is one point I don't know whether I got it correct: in utils/main_utils.py:transform_pt_depth_scannet_torch(), it requires bx and by from camera intrinsic matrix. I don't know what they mean and set them to 0s.

Could you provide any insights on refining the results? e.g. lower image resolution for SAM, change filter parameters, etc.

First frame rgb image:

Final segmented point cloud, the floor is segmented well, but for other parts seem only around the first frame viewpoint:

Start by reproducing the RedWood bedroom dataset case with the reported image and point-cloud sizes, then inspect utils/main_utils.py:transform_pt_depth_scannet_torch() and how bx and by are derived from the camera intrinsics. Compare the proposal, 2D-guided filtering, and prompt-consolidation counts. Done means identifying the cause of the viewpoint-limited segmentation or documenting the correct parameters and confirmed settings.

Written by the indexing model from the issue text.