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/DITR

DITR

Reported on 23 benchmarks across 4 tasks · 1 paper · 19 SOTA

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

Medical8 results

Semantic SegmentationonScanNet
val mIoU· 2025-03-24
80.5
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
Semantic SegmentationonScanNet200
test mIoU· 2025-03-24
44.9
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
Semantic SegmentationonScanNet200
val mIoU· 2025-03-24
41.2
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
Semantic SegmentationonWaymo Open Dataset
mIoU· 2025-03-24
73.3
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
Semantic SegmentationonScanNet++
Top-1 IoU· 2025-03-24
0.525
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
Semantic SegmentationonScanNet++
Top-3 IoU· 2025-03-24
0.762
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
Semantic SegmentationonScanNet
test mIoU· 2025-03-24
79.7
best: 79.8 (PTv3 ARKit LabelMaker)
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
Semantic SegmentationonS3DIS Area5
mIoU· 2025-03-24
74.1
best: 76 (Sonata + PTv3)
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944

Audio8 results

10-shot image generationonScanNet
val mIoU· 2025-03-24
80.5
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
10-shot image generationonScanNet200
test mIoU· 2025-03-24
44.9
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
10-shot image generationonScanNet200
val mIoU· 2025-03-24
41.2
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
10-shot image generationonWaymo Open Dataset
mIoU· 2025-03-24
73.3
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
10-shot image generationonScanNet++
Top-1 IoU· 2025-03-24
0.525
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
10-shot image generationonScanNet++
Top-3 IoU· 2025-03-24
0.762
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
10-shot image generationonScanNet
test mIoU· 2025-03-24
79.7
best: 79.8 (PTv3 ARKit LabelMaker)
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
10-shot image generationonS3DIS Area5
mIoU· 2025-03-24
74.1
best: 76 (Sonata + PTv3)
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944

Computer Vision7 results

3D Semantic SegmentationonScanNet200
test mIoU· 2025-03-24
44.9
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
3D Semantic SegmentationonScanNet200
val mIoU· 2025-03-24
41.2
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
3D Semantic SegmentationonWaymo Open Dataset
mIoU· 2025-03-24
73.3
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
3D Semantic SegmentationonScanNet++
Top-1 IoU· 2025-03-24
0.525
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
3D Semantic SegmentationonScanNet++
Top-3 IoU· 2025-03-24
0.762
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
LIDAR Semantic SegmentationonnuScenes
test mIoU· 2025-03-24
0.851
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944
LIDAR Semantic SegmentationonnuScenes
val mIoU· 2025-03-24
0.842
SOTA
DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation arXiv:2503.18944