AI Paper Atlas

Research map / 3D vision / Human pose estimation

Affordance-Guided Diffusion Prior for 3D Hand Reconstruction

Naru Suzuki, Takehiko Ohkawa, Tatsuro Banno, Jihyun Lee, Ryosuke Furuta, Yoichi Sato

ECCV 2026 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression

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
Refine WiLoR with affordance-guided diffusion priorWiLoR · HOGraspNetPA-MPJPE avg: 8.22 -> 7.53Improved
Refine WiLoR with affordance prior, high occlusion subsetWiLoR · HOGraspNetPA-MPJPE high occlusion: 12.41 -> 9.37Improved
Refine Hamba with affordance priorHamba · HOGraspNetPA-MPJPE avg: 8.46 -> 7.85Improved
Refine WiLoR with affordance priorWiLoR · HO3DPA-MPJPE avg: 7.43 -> 7.37No clear effect
Apply InterHandGen diffusion prior without contextWiLoR · HOGraspNetPA-MPJPE avg: 8.22 -> 8.99Hurt
Add simple VLM captions as text condition (ablation)AffHandGen · HOGraspNetPA-MPJPE avg: 9.28 -> 8.67 (no RGB); 7.90 -> 7.76 (RGB)No clear effect
Add affordance descriptions as text condition (ablation)AffHandGen · HOGraspNetPA-MPJPE avg: 7.90 -> 7.53Improved
Add RGB image features as condition (ablation)AffHandGen · HOGraspNetPA-MPJPE avg: 8.43 -> 7.53Improved
Use ground-truth grasp instead of predicted grasp (ablation)AffHandGen · HOGraspNetPA-MPJPE avg: 7.53 -> 7.51No clear effect
Add Mistral summarization of Qwen keywords (ablation)AffHandGen · HOGraspNetPA-MPJPE avg: 7.59 -> 7.53Improved
Add 2D keypoint guidance (ablation)AffHandGen refinement · HOGraspNetPA-MPJPE avg: 7.65 -> 7.53Improved
Use HaMeR+DistilBERT encoders instead of CLIP (ablation)AffHandGen · HOGraspNetPA-MPJPE avg: 11.36 -> 7.53Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 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