Learning 3D Human Pose from Structure and Motion

ECCV 2018 Rishabh DabralAnurag MundhadaUday KusupatiSafeer AfaqueAbhishek SharmaArjun Jain

3D human pose estimation from a single image is a challenging problem, especially for in-the-wild settings due to the lack of 3D annotated data. We propose two anatomically inspired loss functions and use them with a weakly-supervised learning framework to jointly learn from large-scale in-the-wild 2D and indoor/synthetic 3D data... (read more)

PDF Abstract ECCV 2018 PDF ECCV 2018 Abstract
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
3D Human Pose Estimation Human3.6M TP-Net Average MPJPE (mm) 52.1 # 25

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet