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/Point-GCC+TR3D

Point-GCC+TR3D

Reported on 36 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.

Methodology24 results

3DonS3DIS
mAP@0.25· uses extra data· 2023-05-31
75.1
best: 75.2 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3DonS3DIS
mAP@0.5· uses extra data· 2023-05-31
56.7
best: 60.8 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D ClassificationonS3DIS
mAP@0.25· uses extra data· 2023-05-31
75.1
best: 75.2 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D ClassificationonS3DIS
mAP@0.5· uses extra data· 2023-05-31
56.7
best: 60.8 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D Object DetectiononS3DIS
mAP@0.25· uses extra data· 2023-05-31
75.1
best: 75.2 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D Object DetectiononS3DIS
mAP@0.5· uses extra data· 2023-05-31
56.7
best: 60.8 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
16konS3DIS
mAP@0.25· uses extra data· 2023-05-31
75.1
best: 75.2 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
16konS3DIS
mAP@0.5· uses extra data· 2023-05-31
56.7
best: 60.8 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3DonSUN-RGBD val
mAP@0.25· 2023-05-31
67.7
best: 69.7 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3DonSUN-RGBD val
mAP@0.5· 2023-05-31
51
best: 54 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3DonScanNetV2
mAP@0.25· 2023-05-31
73.1
best: 78.8 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3DonScanNetV2
mAP@0.5· 2023-05-31
59.6
best: 67.9 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D ClassificationonSUN-RGBD val
mAP@0.25· 2023-05-31
67.7
best: 69.7 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D ClassificationonSUN-RGBD val
mAP@0.5· 2023-05-31
51
best: 54 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D ClassificationonScanNetV2
mAP@0.25· 2023-05-31
73.1
best: 78.8 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D ClassificationonScanNetV2
mAP@0.5· 2023-05-31
59.6
best: 67.9 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D Object DetectiononSUN-RGBD val
mAP@0.25· 2023-05-31
67.7
best: 69.7 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D Object DetectiononSUN-RGBD val
mAP@0.5· 2023-05-31
51
best: 54 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D Object DetectiononScanNetV2
mAP@0.25· 2023-05-31
73.1
best: 78.8 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
2D Object DetectiononScanNetV2
mAP@0.5· 2023-05-31
59.6
best: 67.9 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
16konSUN-RGBD val
mAP@0.25· 2023-05-31
67.7
best: 69.7 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
16konSUN-RGBD val
mAP@0.5· 2023-05-31
51
best: 54 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
16konScanNetV2
mAP@0.25· 2023-05-31
73.1
best: 78.8 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
16konScanNetV2
mAP@0.5· 2023-05-31
59.6
best: 67.9 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623

Computer Vision12 results

Object DetectiononS3DIS
mAP@0.25· uses extra data· 2023-05-31
75.1
best: 75.2 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
Object DetectiononS3DIS
mAP@0.5· uses extra data· 2023-05-31
56.7
best: 60.8 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3D Object DetectiononS3DIS
mAP@0.25· uses extra data· 2023-05-31
75.1
best: 75.2 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3D Object DetectiononS3DIS
mAP@0.5· uses extra data· 2023-05-31
56.7
best: 60.8 (UniDet3D)
SOTA
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
Object DetectiononSUN-RGBD val
mAP@0.25· 2023-05-31
67.7
best: 69.7 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
Object DetectiononSUN-RGBD val
mAP@0.5· 2023-05-31
51
best: 54 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
Object DetectiononScanNetV2
mAP@0.25· 2023-05-31
73.1
best: 78.8 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
Object DetectiononScanNetV2
mAP@0.5· 2023-05-31
59.6
best: 67.9 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3D Object DetectiononSUN-RGBD val
mAP@0.25· 2023-05-31
67.7
best: 69.7 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3D Object DetectiononSUN-RGBD val
mAP@0.5· 2023-05-31
51
best: 54 (Point-GCC+TR3D+FF)
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3D Object DetectiononScanNetV2
mAP@0.25· 2023-05-31
73.1
best: 78.8 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623
3D Object DetectiononScanNetV2
mAP@0.5· 2023-05-31
59.6
best: 67.9 (DEST (based on V-DETR) (TTA))
Point-GCC: Universal Self-supervised 3D Scene Pre-training via Geometry-Color Contrast arXiv:2305.19623