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/Swin3D-L+CAGroup3D

Swin3D-L+CAGroup3D

Reported on 12 benchmarks across 6 tasks · 1 paper · 12 SOTA

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

Methodology8 results

3DonScanNetV2
mAP@0.25· uses extra data· 2023-04-14
76.4
best: 78.8 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
3DonScanNetV2
mAP@0.5· uses extra data· 2023-04-14
63.2
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
2D ClassificationonScanNetV2
mAP@0.25· uses extra data· 2023-04-14
76.4
best: 78.8 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
2D ClassificationonScanNetV2
mAP@0.5· uses extra data· 2023-04-14
63.2
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
2D Object DetectiononScanNetV2
mAP@0.25· uses extra data· 2023-04-14
76.4
best: 78.8 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
2D Object DetectiononScanNetV2
mAP@0.5· uses extra data· 2023-04-14
63.2
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
16konScanNetV2
mAP@0.25· uses extra data· 2023-04-14
76.4
best: 78.8 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
16konScanNetV2
mAP@0.5· uses extra data· 2023-04-14
63.2
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906

Computer Vision4 results

Object DetectiononScanNetV2
mAP@0.25· uses extra data· 2023-04-14
76.4
best: 78.8 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
Object DetectiononScanNetV2
mAP@0.5· uses extra data· 2023-04-14
63.2
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
3D Object DetectiononScanNetV2
mAP@0.25· uses extra data· 2023-04-14
76.4
best: 78.8 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906
3D Object DetectiononScanNetV2
mAP@0.5· uses extra data· 2023-04-14
63.2
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Swin3D: A Pretrained Transformer Backbone for 3D Indoor Scene Understanding arXiv:2304.06906