AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D Human Shape and Pose from a Single Low-Resolution Image with Self-Supervised Learning

Xiangyu Xu, Hao Chen, Francesc Moreno-Noguer, László A. Jeni, Fernando De la Torre

ECCV 2020 · 3D vision › Human pose estimation · approach: Human shape and pose regression · 47 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
use resolution-aware network instead of plain ResNet50 (ablation)baseline with basic loss · 3DPW (res 32)MPJPE: 143.63 -> 135.29Improved
add self-supervision loss (ablation)resolution-aware network · 3DPW (res 32)MPJPE: 135.29 -> 124.23Improved
add self-supervision loss (ablation)baseline network · 3DPW (res 32)MPJPE: 143.63 -> 128.88Improved
add resolution-aware network on top of self-supervision (ablation)baseline + SS · 3DPW (res 32)MPJPE: 128.88 -> 124.23Improved
add contrastive feature loss (ablation)RA+SS · 3DPW (res 32)MPJPE: 124.23 -> 117.12Improved
add MSE feature loss (ablation)RA+SS · 3DPW (res 32)MPJPE: 124.23 -> 124.85No clear effect
add cosine distance feature loss (ablation)RA+SS · 3DPW (res 32)MPJPE: 124.23 -> 125.08No clear effect
add progressive training (ablation)full model · 3DPW (res 32)MPJPE: 127.05 -> 117.12Improved
use directional self-supervision instead of original (ablation)full model · 3DPW (res 32)MPJPE: 156.25 -> 117.12Improved
add hierarchical supervision from all resolutions (ablation)full model · 3DPW (res 32)MPJPE: 122.01 -> 117.12Improved
use proposed method instead of FeaEN baselineRSC-Net · 3DPW (res 32)MPJPE: 143.51 -> 117.12Improved
use proposed method instead of SPINRSC-Net · MPI-INF-3DHP (res 32)MPJPE: 127.27 -> 115.80Improved

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