AI Paper Atlas

Research map / 3D vision / Human pose estimation

Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle

Miroslav Purkrabek, Jiri Matas

ICCV 2025 · 3D vision › Human pose estimation · approach: Multi-person 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 mask conditioning (MaskPose) to ViTPoseViTPose-B · OCHuman testpose AP: 42.6 -> 45.0Improved
add second BMP iterationBBox-Mask-Pose · OCHuman testpose AP: 46.6 -> 49.3Improved
add second BMP iterationBBox-Mask-Pose · COCO valpose AP: 76.5 -> 76.5No clear effect
add second BMP iterationBBox-Mask-Pose · OCHuman testbbox AP: 32.4 -> 35.9Improved
add SAM to the loop (versus omitting SAM) (ablation)BMP 2x · OCHuman valbbox AP: 30.8 -> 32.1Improved
add SAM to the loop (versus omitting SAM) (ablation)BMP 2x · OCHuman valpose AP: 47.0 -> 48.6Improved
add keypoint prompts to SAM bounding-box prompt (ablation)BMP 2x · OCHuman valbbox AP: 31.9 -> 32.1Improved
add keypoint prompts to SAM bounding-box prompt (ablation)BMP 2x · OCHuman valpose AP: 47.3 -> 48.6Improved
rerun pose estimation on SAM-refined masks (ablation)BMP 1x · OCHuman valpose AP: 45.3 -> 46.4Improved
use pose-selected instances (c and d) rather than confidence only (ablation)SAM prompting · OCHuman valbbox AP: 29.7 -> 32.7Improved
add negative keypoint prompts with bounding box (ablation)SAM prompting · OCHuman valsegm AP: 30.9 -> 28.2Hurt
use batch processing of all instances (ablation)SAM prompting · OCHuman valbbox AP: 29.3 -> 29.3No clear effect

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