AI Paper Atlas

Research map / 3D vision / Human pose estimation

ConceptPose: Training-Free Zero-Shot Object Pose Estimation using Concept Vectors

Liming Kuang, Yordanka Velikova, Mahdi Saleh, Jan-Nico Zaech, Danda Pani Paudel, Benjamin Busam

CVPR 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 2 citations (OpenAlex)

Read the paper

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
increase number of concepts from 3 to 20 (ablation)ConceptPose · REAL275ADD(-S) recall: 64.3 -> 74.0Improved
increase number of concepts from 15 to 20 (ablation)ConceptPose · REAL275ADD(-S) recall: 72.0 -> 74.0Improved
use continuous concept vectors instead of binary masks (ablation)ConceptPose · REAL275ADD(-S) recall: 30.5 -> 71.5Improved
use SigLIP2-giant instead of SigLIP2-large (ablation)ConceptPose · REAL275ADD(-S) recall: 67.0 -> 72.0Improved
use SigLIP2-giant instead of CLIP ViT-L/14@336px (ablation)ConceptPose · REAL275ADD(-S) recall: 54.1 -> 72.0Improved
use SigLIP2-giant GradCAM instead of DINOv3 + dinotxt patch similarity (ablation)ConceptPose · REAL275ADD(-S) recall: 62.3 -> 72.0Improved
add voxelization (64^3 grid) (ablation)ConceptPose · REAL275ADD(-S) recall: 71.5 -> 71.2Mixed
add voxelization (64^3 grid) (ablation)ConceptPose · LINEMODADD(-S) recall: 38.6 -> 36.8Mixed
use geometric prompt with category renderings instead of default part-name prompt (ablation)ConceptPose · REAL275ADD(-S) recall: 71.5 -> 71.9No clear effect
use affordance prompt instead of default prompt (ablation)ConceptPose · REAL275ADD(-S) recall: 71.5 -> 68.6Hurt
use cosine instead of bidirectional KL correspondence (ablation)ConceptPose · REAL275ADD(-S) recall: 72.0 -> 72.1No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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