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/OneFormer3D

OneFormer3D

Reported on 43 benchmarks across 12 tasks · 1 paper · 19 SOTA

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

Computer Vision19 results

Instance SegmentationonS3DIS
AP@50· 2023-11-24
75.8
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Instance SegmentationonS3DIS
mPrec· 2023-11-24
82.3
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Semantic SegmentationonS3DIS
mIoU (Area-5)· 2023-11-24
72.4
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Panoptic SegmentationonScanNet
PQ· 2023-11-24
71.2
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Panoptic SegmentationonScanNet
PQ_st· 2023-11-24
86.1
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Panoptic SegmentationonScanNet
PQ_th· 2023-11-24
69.6
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Panoptic SegmentationonScanNetV2
PQ· 2023-11-24
71.2
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Instance SegmentationonS3DIS
AP@50· 2023-11-24
75.8
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Instance SegmentationonS3DIS
mPrec· 2023-11-24
82.3
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Object DetectiononScanNetV2
mAP@0.25· 2023-11-24
76.9
best: 78.8 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Object DetectiononScanNetV2
mAP@0.5· 2023-11-24
65.3
best: 67.9 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Instance SegmentationonS3DIS
mAP· 2023-11-24
63
best: 64.5 (Mask3D)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Instance SegmentationonS3DIS
mRec· 2023-11-24
74.1
best: 77.1 (ISBNet)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Semantic SegmentationonScanNet200
val mIoU· 2023-11-24
30.1
best: 41.2 (DITR)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Semantic SegmentationonS3DIS
mIoU (6-Fold)· 2023-11-24
75
best: 76 (Superpoint Transformer)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Object DetectiononScanNetV2
mAP@0.25· 2023-11-24
76.9
best: 78.8 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Object DetectiononScanNetV2
mAP@0.5· 2023-11-24
65.3
best: 67.9 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Instance SegmentationonS3DIS
mAP· 2023-11-24
63
best: 64.5 (Mask3D)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3D Instance SegmentationonS3DIS
mRec· 2023-11-24
74.1
best: 77.1 (ISBNet)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405

Medical8 results

Semantic SegmentationonScanNet
PQ· 2023-11-24
71.2
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Semantic SegmentationonScanNet
PQ_st· 2023-11-24
86.1
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Semantic SegmentationonScanNet
PQ_th· 2023-11-24
69.6
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Semantic SegmentationonScanNetV2
PQ· 2023-11-24
71.2
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Semantic SegmentationonS3DIS
mIoU (Area-5)· 2023-11-24
72.4
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Semantic SegmentationonScanNet
val mIoU· 2023-11-24
76.6
best: 80.5 (DITR)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Semantic SegmentationonScanNet200
val mIoU· 2023-11-24
30.1
best: 41.2 (DITR)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
Semantic SegmentationonS3DIS
mIoU (6-Fold)· 2023-11-24
75
best: 76 (Superpoint Transformer)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405

Audio8 results

10-shot image generationonScanNet
PQ· 2023-11-24
71.2
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
10-shot image generationonScanNet
PQ_st· 2023-11-24
86.1
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
10-shot image generationonScanNet
PQ_th· 2023-11-24
69.6
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
10-shot image generationonScanNetV2
PQ· 2023-11-24
71.2
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
10-shot image generationonS3DIS
mIoU (Area-5)· 2023-11-24
72.4
SOTA
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
10-shot image generationonScanNet
val mIoU· 2023-11-24
76.6
best: 80.5 (DITR)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
10-shot image generationonScanNet200
val mIoU· 2023-11-24
30.1
best: 41.2 (DITR)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
10-shot image generationonS3DIS
mIoU (6-Fold)· 2023-11-24
75
best: 76 (Superpoint Transformer)
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405

Methodology8 results

3DonScanNetV2
mAP@0.25· 2023-11-24
76.9
best: 78.8 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
3DonScanNetV2
mAP@0.5· 2023-11-24
65.3
best: 67.9 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
2D ClassificationonScanNetV2
mAP@0.25· 2023-11-24
76.9
best: 78.8 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
2D ClassificationonScanNetV2
mAP@0.5· 2023-11-24
65.3
best: 67.9 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
2D Object DetectiononScanNetV2
mAP@0.25· 2023-11-24
76.9
best: 78.8 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
2D Object DetectiononScanNetV2
mAP@0.5· 2023-11-24
65.3
best: 67.9 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
16konScanNetV2
mAP@0.25· 2023-11-24
76.9
best: 78.8 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405
16konScanNetV2
mAP@0.5· 2023-11-24
65.3
best: 67.9 (DEST (based on V-DETR) (TTA))
OneFormer3D: One Transformer for Unified Point Cloud Segmentation arXiv:2311.14405