V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map

Benchmark Model Rank Results
hand-pose-estimation-on-hands-2017V2V-PoseNet#3Average 3D Error: 9.95
hand-pose-estimation-on-icvl-handsV2V-PoseNet#7Average 3D Error: 6.28
hand-pose-estimation-on-msra-handsV2V-PoseNet#5Average 3D Error: 7.49
hand-pose-estimation-on-nyu-handsV2V-PoseNet#5Average 3D Error: 8.42
pose-estimation-on-itop-front-viewV2V-PoseNet#4Mean mAP: 88.74
pose-estimation-on-itop-top-viewV2V-PoseNet#3Mean mAP: 83.44