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/V2V-PoseNet

V2V-PoseNet

Reported on 26 benchmarks across 5 tasks · 1 paper · 26 SOTA

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

Computer Vision10 results

HandonMSRA Hands
Average 3D Error· 2017-11-20
7.49
best: 7.13 (TriHorn-Net)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
HandonICVL Hands
Average 3D Error· 2017-11-20
6.28
best: 4.79 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
HandonNYU Hands
Average 3D Error· 2017-11-20
8.42
best: 6.4 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
HandonHANDS 2017
Average 3D Error· 2017-11-20
9.95
best: 7.48 (AWR)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Pose EstimationonITOP top-view
Mean mAP· 2017-11-20
83.44
best: 86.92 (DECA-D3)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Pose Estimationon ITOP front-view
Mean mAP· 2017-11-20
88.74
best: 93.38 (AdaPose)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Pose EstimationonMSRA Hands
Average 3D Error· 2017-11-20
7.49
best: 7.13 (TriHorn-Net)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Pose EstimationonICVL Hands
Average 3D Error· 2017-11-20
6.28
best: 4.79 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Pose EstimationonNYU Hands
Average 3D Error· 2017-11-20
8.42
best: 6.4 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Pose EstimationonHANDS 2017
Average 3D Error· 2017-11-20
9.95
best: 7.48 (AWR)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399

Methodology6 results

3DonITOP top-view
Mean mAP· 2017-11-20
83.44
best: 86.92 (DECA-D3)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
3Don ITOP front-view
Mean mAP· 2017-11-20
88.74
best: 93.38 (AdaPose)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
3DonMSRA Hands
Average 3D Error· 2017-11-20
7.49
best: 7.13 (TriHorn-Net)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
3DonICVL Hands
Average 3D Error· 2017-11-20
6.28
best: 4.79 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
3DonNYU Hands
Average 3D Error· 2017-11-20
8.42
best: 6.4 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
3DonHANDS 2017
Average 3D Error· 2017-11-20
9.95
best: 7.48 (AWR)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399

Audio6 results

1 Image, 2*2 StitchionITOP top-view
Mean mAP· 2017-11-20
83.44
best: 86.92 (DECA-D3)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
1 Image, 2*2 Stitchion ITOP front-view
Mean mAP· 2017-11-20
88.74
best: 93.38 (AdaPose)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
1 Image, 2*2 StitchionMSRA Hands
Average 3D Error· 2017-11-20
7.49
best: 7.13 (TriHorn-Net)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
1 Image, 2*2 StitchionICVL Hands
Average 3D Error· 2017-11-20
6.28
best: 4.79 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
1 Image, 2*2 StitchionNYU Hands
Average 3D Error· 2017-11-20
8.42
best: 6.4 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
1 Image, 2*2 StitchionHANDS 2017
Average 3D Error· 2017-11-20
9.95
best: 7.48 (AWR)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399

Graphs4 results

Hand Pose EstimationonMSRA Hands
Average 3D Error· 2017-11-20
7.49
best: 7.13 (TriHorn-Net)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Hand Pose EstimationonICVL Hands
Average 3D Error· 2017-11-20
6.28
best: 4.79 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Hand Pose EstimationonNYU Hands
Average 3D Error· 2017-11-20
8.42
best: 6.4 (Virtual View Selection)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399
Hand Pose EstimationonHANDS 2017
Average 3D Error· 2017-11-20
9.95
best: 7.48 (AWR)
SOTA
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map arXiv:1711.07399