AI Paper Atlas

Research map / 3D vision / Human pose estimation

Learning Realistic Human Reposing Using Cyclic Self-Supervision With 3D Shape, Pose, and Appearance Consistency

Soubhik Sanyal, Alex Vorobiov, Timo Bolkart, Matthew Loper, Betty Mohler, Larry S. Davis, Javier Romero, Michael J. Black

ICCV 2021 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 19 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 shape loss (ablation)SPICE · DeepFashionFID: 8.7 -> 7.8Improved
add pose loss (ablation)SPICE · DeepFashionFID: 8.4 -> 7.8Improved
add appearance loss (ablation)SPICE · DeepFashionFID: 9.9 -> 7.8Improved
condition discriminator on colored mesh renderings (ablation)SPICE · DeepFashionFID: 10.0 -> 7.8Improved
add shape loss (ablation)SPICE · DeepFashionLPIPS: 0.166 -> 0.164No clear effect
add pose loss (ablation)SPICE · DeepFashionLPIPS: 0.165 -> 0.164No clear effect
add appearance loss (ablation)SPICE · DeepFashionLPIPS: 0.164 -> 0.164No clear effect
condition discriminator on colored mesh renderings (ablation)SPICE · DeepFashionLPIPS: 0.167 -> 0.164Improved
use self-supervised SPICE instead of unpaired baseline PGSPTunpaired reposing · DeepFashionFID: 29.9 -> 7.8Improved
compute FID with raw reference vs JPEG-80 generated images (mismatched compression)FID evaluation · DeepFashionFID: 6.9 -> 12.1Hurt

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