AI Paper Atlas

Research map / 3D vision / Face and shape

Unsupervised Shape and Pose Disentanglement for 3D Meshes

Keyang Zhou, Bharat Lal Bhatnagar, Gerard Pons-Moll

ECCV 2020 · 3D vision › Face and shape · approach: Articulated and non-rigid shape learning · 73 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 self-consistency loss to cross-consistency (ablation)Ours · AMASS pose transfermean error (mm): 23.83 -> 19.43Improved
add ARAP deformation in the training loop (ablation)Ours · AMASS pose transfermean error (mm): 20.27 -> 19.43Improved
replace pose supervision with self-consistencyOurs supervised · AMASS pose transfermean error (mm): 15.44 -> 19.43Mixed
use unsupervised mesh disentanglement instead of GDVAEGDVAE · AMASS pose transfermean error (mm): 54.44 -> 19.43Improved
keep full latent dimension instead of PCA reductionOurs · AMASS shape retrieval (shape code)E_beta: 0.34 -> 0.14Improved
reduce latent dimension with PCA for pose retrievalOurs · AMASS pose retrieval (pose code)E_beta: 0.92 -> 2.14Mixed
use Ours instead of Jiang et al. on COMAJiang et al. · COMA expression extrapolationaverage error (mm): 1.64 -> 1.28Improved
add edge length constraints and other local shape-preserving losses (ablation)Ours · AMASSreconstructionNo clear effect

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