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/PBNet

PBNet

Reported on 22 benchmarks across 8 tasks · 1 paper · 12 SOTA

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

Computer Vision14 results

Object DetectiononScanNetV2
mAP@0.5· 2022-07-22
60.1
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
Instance SegmentationonS3DIS
AP@50· 2022-07-22
70.6
best: 75.8 (OneFormer3D)
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
Instance SegmentationonS3DIS
mAP· 2022-07-22
59.5
best: 64.5 (Mask3D)
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
Instance SegmentationonScanNet(v2)
mAP· 2022-07-22
57.3
best: 62.2 (Relation3D)
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
3D Object DetectiononScanNetV2
mAP@0.5· 2022-07-22
60.1
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
3D Instance SegmentationonS3DIS
AP@50· 2022-07-22
70.6
best: 75.8 (OneFormer3D)
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
3D Instance SegmentationonS3DIS
mAP· 2022-07-22
59.5
best: 64.5 (Mask3D)
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
3D Instance SegmentationonScanNet(v2)
mAP· 2022-07-22
57.3
best: 62.2 (Relation3D)
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
Object DetectiononScanNetV2
mAP@0.25· 2022-07-22
69.3
best: 78.8 (DEST (based on V-DETR) (TTA))
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
Instance SegmentationonScanNet(v2)
mAP @ 50· 2022-07-22
74.7
best: 81.6 (Relation3D)
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
Instance SegmentationonScanNet(v2)
mAP@25· 2022-07-22
82.5
best: 90.1 (Relation3D)
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
3D Object DetectiononScanNetV2
mAP@0.25· 2022-07-22
69.3
best: 78.8 (DEST (based on V-DETR) (TTA))
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
3D Instance SegmentationonScanNet(v2)
mAP @ 50· 2022-07-22
74.7
best: 81.6 (Relation3D)
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
3D Instance SegmentationonScanNet(v2)
mAP@25· 2022-07-22
82.5
best: 90.1 (Relation3D)
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209

Methodology8 results

3DonScanNetV2
mAP@0.5· 2022-07-22
60.1
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
2D ClassificationonScanNetV2
mAP@0.5· 2022-07-22
60.1
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
2D Object DetectiononScanNetV2
mAP@0.5· 2022-07-22
60.1
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
16konScanNetV2
mAP@0.5· 2022-07-22
60.1
best: 67.9 (DEST (based on V-DETR) (TTA))
SOTA
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
3DonScanNetV2
mAP@0.25· 2022-07-22
69.3
best: 78.8 (DEST (based on V-DETR) (TTA))
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
2D ClassificationonScanNetV2
mAP@0.25· 2022-07-22
69.3
best: 78.8 (DEST (based on V-DETR) (TTA))
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
2D Object DetectiononScanNetV2
mAP@0.25· 2022-07-22
69.3
best: 78.8 (DEST (based on V-DETR) (TTA))
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209
16konScanNetV2
mAP@0.25· 2022-07-22
69.3
best: 78.8 (DEST (based on V-DETR) (TTA))
Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization arXiv:2207.11209