AI Paper Atlas

Research map / 3D vision / Human pose estimation

DGG-HMR: Multi-Person Human Mesh Recovery with Depth-Guided Geometric Anchoring

Yanjie Li, Le Hui, Yali Peng, Shigang Liu

ICML 2026 · 3D vision › Human pose estimation · approach: Human mesh recovery from images

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 instance-level pelvis depth token concatenated with image tokens (ablation)DGG-HMR baseline · AGORA valMPJPE: 77.3 -> 74.3Improved
add instance-level depth token (ablation)DGG-HMR baseline · AGORA valPCDR0.2 (%): 89.3 -> 92.4Improved
add geometry-anchored refinement decoder on top of depth token (ablation)DGG-HMR · AGORA valMPJPE: 74.3 -> 69.0Improved
add geometry-anchored refinement decoder on top of depth token (ablation)DGG-HMR · AGORA valADE (m): 2.20 -> 2.12Improved
use single-stage joint training instead of two-stage (depth pre-training then joint fine-tuning) (ablation)DGG-HMR · AGORA valMPJPE: 75.3 -> 69.0Improved
use single-stage joint training instead of two-stage (ablation)DGG-HMR · AGORA valPCDR0.2 (%): 93.9 -> 94.8Improved
fuse geometry priors into image features (feature-level concatenation) rather than injecting into decoder queries (ablation)DGG-HMR · design discussiondepth ambiguityNo clear effect
increase input resolution from 672 to 896 (ablation)DGG-HMR · 3DPWPA-MPJPE: 40.5 -> 39.0Improved
add instance-aware depth estimator and geometry anchoring versus SAT-HMRDGG-HMR (896) · MuPoTS-3DPCK-All: 89.0 -> 86.2Hurt
add instance-aware depth estimator and geometry anchoring versus SAT-HMRDGG-HMR (896) · 3DPWMPJPE: 63.6 -> 61.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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