AI Paper Atlas

Research map / 3D vision / Human pose estimation

VLM-Guided Group Preference Alignment for Diffusion-based Human Mesh Recovery

Wenhao Shen, Hao Wang, Wanqi Yin, Fayao Liu, Xulei Yang, Chao Liang, Zhongang Cai, Guosheng Lin

CVPR 2026 · 3D vision › Human pose estimation · approach: Human mesh recovery from images · 2 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
replace HMR-Scorer with the VLM critique agent to build the preference dataset (ablation)group preference alignment · 3DPW (InstaVariety, M=100)MPJPE: 54.9 -> 49.9Improved
use group-wise advantage alignment instead of pairwise DPO (ablation)diffusion HMR with critique agent · 3DPW (InstaVariety, M=100)MPJPE: 53.1 -> 49.9Improved
use preference alignment instead of supervised finetuning on pseudo-labels (ablation)base diffusion HMR model · 3DPW (InstaVariety, M=100)MPJPE: 61.3 -> 49.9Improved
add rule memory to the critique agent (ablation)critique agent · GTA-Human II group-wise (PVE)SRCC: 0.597 -> 0.605Improved
add prototype memory to the critique agent (ablation)critique agent · GTA-Human II group-wise (PVE)SRCC: 0.590 -> 0.605Improved
add self-reflection rule mining to the critique agent (ablation)critique agent · GTA-Human II group-wise (PVE)SRCC: 0.534 -> 0.605Improved
add self-reflection rule mining to the critique agent (ablation)critique agent · DNA-Rendering group-wise (PVE)SRCC: 0.568 -> 0.633Improved
add self-reflection to the critique agent (ablation)critique agent · GTA-Human II point-wise (PVE)PLCC: 0.610 -> 0.695Improved
add prototype memory to the critique agent (ablation)critique agent · GTA-Human II point-wise (PVE)PLCC: 0.645 -> 0.695Improved
add rule memory to the critique agent (ablation)critique agent · GTA-Human II point-wise (PVE)PLCC: 0.683 -> 0.695Improved
increase number of hypotheses M from 10 to 100 to 200Ours · 3DPWMPJPE: 59.3 -> 52.5 -> 51.0Improved
finetune with group preference alignment instead of ADHMR DPOdiffusion HMR · 3DPWMPJPE: 57.2 -> 52.5Improved

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