AI Paper Atlas

Research map / 3D vision / Human pose estimation

Weakly Supervised 3D Human Pose and Shape Reconstruction with Normalizing Flows

Andrei Zanfir, Eduard Gabriel Bazavan, Hongyi Xu, William T. Freeman, Rahul Sukthankar, Cristian Sminchisescu

ECCV 2020 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 136 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add body part alignment (BA) loss to keypoint alignment in optimization (ablation)FS+OPT · 3DPW test (static)MPJPE-PA (mm): 60.3 -> 58.87Improved
add body part alignment (BA) loss to keypoint alignment in optimization (ablation)FS+OPT · 3DPW test (static)MPJPE (mm): 95 -> 91.4Improved
add weakly supervised refinement on COCO after full supervisionFS+OPT (KA+BA) · 3DPW test (static)MPJPE-PA (mm): 58.87 -> 57.1Improved
add keypoint-only optimization on top of the fully supervised model (ablation)FS · 3DPW test (static)MPJPE (mm): 95 -> 95No clear effect
add weakly supervised losses with only 20% of labeled H80K (ablation)FS · H80K testMPJPE (mm): 117 -> 97Improved
add weakly supervised losses starting from random initialization (0% supervision) (ablation)FS · H80K testMPJPE (mm): 649 -> 123Improved
add weakly supervised losses with 100% of labeled H80K (ablation)FS · H80K testMPJPE (mm): 83 -> 84No clear effect
increase temporal window from 4 to 16 frames in video optimization (ablation)FS+WS+OPT(KA+BA+S) · 3DPW test (video)MPJPE (mm): 84.5 -> 80.2Improved
add weakly supervised refinement before 16-frame smoothed optimization (ablation)FS+OPT(KA+BA+S, 16 frames) · 3DPW test (video)MPJPE-PA (mm): 52.2 -> 49.8Improved
add KA+BA instead of KA only during self-supervised refinement with 100% data (ablation)WS · 3DPW test (COCO+OpenImages)mIOU: 44.0 -> 50.0Improved
increase self-supervised data from 10% to 100% with KA+BA (ablation)WS+KA+BA · 3DPW test (COCO+OpenImages)2D joint error (pixels): 7.2 -> 5.8Improved
add weakly supervised refinement to the fully supervised network (ablation)FS · 3DPW test (COCO+OpenImages)2D joint error (pixels): 9.13 -> 5.8Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy