AI Paper Atlas

Research map / 3D vision / Human pose estimation

Category-Level Articulated Object Pose Estimation via Pose–Shape Hypothesis Generation and Verification

Kaifeng Tang, Chi Xu, Xin Ao, Yuting Ge, Tingrui Guo, Jun Zhou

ECCV 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 0 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
model joint pose-shape distribution and verify with instance-specific joints (vs pose-only generation) (ablation)pose-shape hypothesis generator · HOI4DmAP 5deg5cm (%): 51.1 -> 59.2Improved
add shape distribution without verification (ablation)pose-only generator · HOI4DmAP 5deg5cm (%): 51.1 -> 48.3Hurt
add joint verification to pose-only hypotheses (ablation)pose-only generator · HOI4DmAP 5deg5cm (%): 51.1 -> 53.8Improved
add SDF shape-consistency verification and denoising (ablation)pose-shape generator + joint verification · HOI4DmAP 5deg5cm (%): 59.2 -> 61.0Improved
add shape verification without denoising (SDF) (ablation)pose-shape generator + joint verification · HOI4DmAP 5deg5cm (%): 59.2 -> 54.4Hurt
add part-level point cloud denoising to SDF shape verification (ablation)verification module · HOI4DmAP 5deg5cm (%): 54.4 -> 61.0Improved
use SDF scoring instead of unidirectional Chamfer Distance for shape verification (ablation)verification module · HOI4DmAP 5deg5cm (%): 60.2 -> 61.0Improved
use generation-and-verification instead of regression or tracking baselinesfull method · HOI4DmAP 5deg5cm (%): 44.7 (PPF-Tracker) -> 61.0Improved
use single-view method versus sequence-based PPF-Tracker on synthetic datafull method · PM-VideosTerr (m): Rerr 4.1 -> 3.0; Terr 0.049 -> 0.059 (Laptop)Mixed
use learned SDF shape decoder vs CARTO decoderfull method · HOI4D shape reconstructionCD-L2: 0.054 -> 0.016Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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