AI Paper Atlas

Research map / 3D vision / Human pose estimation

Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes

Tom Fischer, Xiaojie Zhang, Eddy Ilg

ICCV 2025 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 5 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
add adapters to DINOv2 blocks (ablation)Ours · REAL275NIoU50: -21.0Improved
add CrossAttention foreground modeling (mask ignored at inference) (ablation)Ours · REAL275NIoU50: -9.4 -> -4.9Improved
use the foreground mask at inference (t1=0.5) (ablation)Ours · REAL275NIoU50: -4.9 -> 0Improved
add instance-level pose refinement (ablation)Ours · REAL275NIoU50: -2.7 -> -2.4Improved
add size optimization from instance correspondences (ablation)Ours · REAL275NIoU75: -3.9 -> +0.1Improved
use tuned threshold t2 optimum for no-CA model (ablation)Ours w/o CA · REAL275NIoU50: -9.4 -> -4.9Improved
single-stage instead of two-stage under image corruptions (ablation)Ours vs LaPose · REAL275 corruptionsNIoU50 loss: -14.0% vs -24.6%Improved
replace Mask-RCNN ROIs with prototype masks (ablation)Ours · REAL275NIoU50: 48.8 -> 53.7Improved
use ground-truth prototype masks instead of own detection (ablation)Ours · REAL275NIoU50: 53.7 -> 55.3Improved
train scale network on prototype projections instead of 2D boxes (ablation)Ours · REAL275 absolute5deg 10cm: 17.7 vs 13.6Mixed

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