Any3DIS

Reported on 6 benchmarks across 3 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

Instance SegmentationonScanNet++
mAP· 2024-11-25
22.2
SOTA
Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking arXiv:2411.16183
3D Open-Vocabulary Instance SegmentationonScanNet200
AP Tail· 2024-11-25
26.4
SOTA
Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking arXiv:2411.16183
3D Open-Vocabulary Instance SegmentationonScanNet200
mAP· 2024-11-25
25.8
SOTA
Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking arXiv:2411.16183
3D Instance SegmentationonScanNet++
mAP· 2024-11-25
22.2
SOTA
Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking arXiv:2411.16183
3D Open-Vocabulary Instance SegmentationonScanNet200
AP Common· 2024-11-25
23.8
best: 24.3 (Open-YOLO 3D)
Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking arXiv:2411.16183
3D Open-Vocabulary Instance SegmentationonScanNet200
AP Head· 2024-11-25
27.4
best: 27.8 (Open-YOLO 3D)
Any3DIS: Class-Agnostic 3D Instance Segmentation by 2D Mask Tracking arXiv:2411.16183