AI Paper Atlas

Research map / 3D vision / Human pose estimation

3D-Object Perception Transformer (3PT)

Agastya Kalra, Tim Salzmann, Guy Stoppi, Dmitrii Marin, Rishav Agarwal, Vage Taamazyan, Martin Bokeloh, Stefan Hinterstoisser, Anton Boykov, Alberto Dall'Olio, Pravin Dangol, Kartik Venkataraman and 1 more

CVPR 2026 · 3D vision › Human pose estimation · approach: Category-level object pose estimation

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
increase training 3D-model vocabulary from 35k to 110k CADs (ablation)3PT-D · BOP-H3 and BOP-Industrial meanAP: 49.7 -> 54.8Improved
train 300k instead of 100k iterations (S=3) (ablation)3PT-D · BOP meanAP: 54.8 -> 56.4Improved
replace MUSE ensemble outputs with 3PT classification, scoring and regression (ablation)MUSE · HANDALAP: 35.7 -> 43.7Improved
train end-to-end 3D-conditioned detector instead of patching MUSE (ablation)MUSE · HANDALAP: 43.7 -> 53.6Improved
apply 3PT multi-view RGB refinement to FRTPose predictions (ablation)FRTPose · BOP-IndustrialAP-mm: 68.3 -> 78.3Improved
add 3PT-D detection and initialization to full pipeline (ablation)3PT-R on FRTPose · BOP-IndustrialAP-mm: 78.3 -> 80.6Improved
apply 3PT-R refinement to Co-Op predictions (ablation)Co-Op · BOP-H3 single-viewAP: 46.4 -> 47.8Improved
use 3PT-D initial poses with K=1 (ablation)3PT-R · BOP-H3 single-viewAP: 47.8 -> 55.1Improved
use K=5 instead of K=1 orientation hypotheses (ablation)3PT · BOP-H3 single-viewAP: 55.1 -> 58.7Improved
use K=8 instead of K=1 rotation hypotheses (ablation)3PT · BOP-IndustrialAP-mm: 71.1 -> 80.9Improved
use 3 refinement iterations instead of 1 (ablation)3PT-R · BOP-IndustrialAP-mm: 77.2 -> 80.9Improved
provide known object classes a priori (ablation)3PT · BOP-IndustrialAP-mm: 80.6 -> 80.9No clear effect

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