scannet200

[CVPR2024] OneFormer3D: One Transformer for Unified Point Cloud Segmentation

[ICLR 2025] Official code of "Segment any 3D Object with Language"

Open-Ended 3D Point Cloud Instance Segmentation (ICCV'25)

Code release for "OV-MAP: Open-Vocabulary Zero-Shot 3D Instance Segmentation Map for Robots"

Code release for "Scene-Q: Confidence-Aware Coarse-to-Fine Querying of 3D Scenes with Selective VLM Reasoning"

Code release for "CDIS : Cross-Dimensional Class-Agnostic 3D Instance Segmentation via 2D Mask Tracking and 3D-2D Projection Merging"

An attention-based solution on long-tail 3D point cloud semantic segmentation tasks.