AI Paper Atlas

Research map / 3D vision / Human pose estimation

Unsupervised 3D Human Pose Representation with Viewpoint and Pose Disentanglement

Qiang Nie, Ziwei Liu, Yunhui Liu

ECCV 2020 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 82 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 bidirectional SeBiReNet (shared hidden states) instead of recursive-only tree (ablation)pose denoising encoder · Cambridge-Imperial APE pose denoising (MLP decoder)MPJPE (mm): 65.76 -> 42.03Improved
share hidden states instead of concatenating subnet outputs (ablation)SeBiReNet · Cambridge-Imperial APE pose denoising (MLP decoder)MPJPE (mm): 75.17 -> 42.03Improved
run SeBiReNet recurrently one more time (ablation)SeBiReNet · Cambridge-Imperial APE pose denoising (MLP decoder)MPJPE (mm): 42.03 -> 41.58No clear effect
use SeBiReNet in decoder as well as encoder (ablation)pose denoising DAE · Cambridge-Imperial APE pose denoising (MLP decoder)MPJPE (mm): 42.03 -> 33.39Improved
add denoising autoencoder with corrupted skeletons (ablation)pose representation · N-UCLAaccuracy (%): 51.53 -> 58.66Improved
add feature decomposition (FD) into view and pose features (ablation)raw DAE · N-UCLAaccuracy (%): 58.66 -> 60.61Improved
add orthogonal regularization L_O on view feature (ablation)raw DAE + FD · N-UCLAaccuracy (%): 60.61 -> 62.55Improved
add feature consistency loss L_f between rotated views (ablation)raw DAE + FD + L_O · N-UCLAaccuracy (%): 62.55 -> 73.81Improved
add reconstruction loss of randomly rotated pose (ablation)raw DAE + FD + L_O + L_f · N-UCLAaccuracy (%): 73.81 -> 76.84Improved
add view-transferred pose losses (full architecture) (ablation)raw DAE + FD + L_O + L_f + L(R*p) · N-UCLAaccuracy (%): 76.84 -> 80.30Improved
add feature consistency loss L_f (ablation)raw DAE + FD + L_O · NTU RGB+Daccuracy (%): 74.46 -> 75.72Improved
add view-transferred pose losses (full architecture) (ablation)raw DAE + FD + L_O + L_f + L(R*p) · NTU RGB+Daccuracy (%): 77.07 -> 79.71Improved

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