Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/MSTA3D

MSTA3D

Reported on 20 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Computer Vision20 results

Instance SegmentationonScanNet(v2)
mRec· 2024-11-04
74.1
SOTA
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonScanNet(v2)
mRec· 2024-11-04
74.1
SOTA
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonS3DIS
AP@50· 2024-11-04
70
best: 75.8 (OneFormer3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonS3DIS
mPrec· 2024-11-04
80.6
best: 82.3 (OneFormer3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonS3DIS
mRec· 2024-11-04
70.1
best: 77.1 (ISBNet)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonScanNet(v2)
mAP· 2024-11-04
56.9
best: 62.2 (Relation3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonScanNet(v2)
mAP @ 50· 2024-11-04
79.5
best: 81.6 (Relation3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonScanNet(v2)
mAP@25· 2024-11-04
87.9
best: 90.1 (Relation3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonScanNet200
mAP· 2024-11-04
26.2
best: 31.5 (ODIN)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonScanNet200
mAP@25· 2024-11-04
40.1
best: 53.1 (ODIN)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
Instance SegmentationonScanNet200
mAP@50· 2024-11-04
35.2
best: 45.3 (ODIN)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonS3DIS
AP@50· 2024-11-04
70
best: 75.8 (OneFormer3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonS3DIS
mPrec· 2024-11-04
80.6
best: 82.3 (OneFormer3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonS3DIS
mRec· 2024-11-04
70.1
best: 77.1 (ISBNet)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonScanNet(v2)
mAP· 2024-11-04
56.9
best: 62.2 (Relation3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonScanNet(v2)
mAP @ 50· 2024-11-04
79.5
best: 81.6 (Relation3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonScanNet(v2)
mAP@25· 2024-11-04
87.9
best: 90.1 (Relation3D)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonScanNet200
mAP· 2024-11-04
26.2
best: 31.5 (ODIN)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonScanNet200
mAP@25· 2024-11-04
40.1
best: 53.1 (ODIN)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781
3D Instance SegmentationonScanNet200
mAP@50· 2024-11-04
35.2
best: 45.3 (ODIN)
MSTA3D: Multi-scale Twin-attention for 3D Instance Segmentation arXiv:2411.01781