ProbPose: A Probabilistic Approach to 2D Human Pose Estimation

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00384019" target="_blank" >RIV/68407700:21230/25:00384019 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/CVPR52734.2025.02526" target="_blank" >https://doi.org/10.1109/CVPR52734.2025.02526</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CVPR52734.2025.02526" target="_blank" >10.1109/CVPR52734.2025.02526</a>

Jazyk výsledku

angličtina

Název v původním jazyce

ProbPose: A Probabilistic Approach to 2D Human Pose Estimation

Popis výsledku v původním jazyce

Current state-of-the-art Human Pose Estimation methods ignore out-of-image keypoints in both training and evaluation and use uncalibrated heatmaps as keypoint location representations. We propose ProbPose, which predicts for each keypoint: a calibrated probability of keypoint presence at each location in the activation window, the probability of being outside of it, and its predicted visibility. To address the lack of evaluation protocols for out-of-image keypoints, we introduce the CropCOCO dataset and the Extended OKS (Ex-OKS) metric, which extends OKS to out-of-image points. Tested on COCO, CropCOCO, and OCHuman, ProbPose shows significant gains in out-of-image keypoint localization while also improving in-image localization through data augmentation. Additionally, the model improves robustness along the edges of the bounding box and offers better flexibility in keypoint evaluation. The code and weights are available on MiraPurkrabek.github.io/ProbPose.

Název v anglickém jazyce

ProbPose: A Probabilistic Approach to 2D Human Pose Estimation

Popis výsledku anglicky

Current state-of-the-art Human Pose Estimation methods ignore out-of-image keypoints in both training and evaluation and use uncalibrated heatmaps as keypoint location representations. We propose ProbPose, which predicts for each keypoint: a calibrated probability of keypoint presence at each location in the activation window, the probability of being outside of it, and its predicted visibility. To address the lack of evaluation protocols for out-of-image keypoints, we introduce the CropCOCO dataset and the Extended OKS (Ex-OKS) metric, which extends OKS to out-of-image points. Tested on COCO, CropCOCO, and OCHuman, ProbPose shows significant gains in out-of-image keypoint localization while also improving in-image localization through data augmentation. Additionally, the model improves robustness along the edges of the bounding box and offers better flexibility in keypoint evaluation. The code and weights are available on MiraPurkrabek.github.io/ProbPose.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/VJ02010041" target="_blank" >VJ02010041: Sada forenzních analytických nástrojů ke zpracování obrazu a videa pro službu kriminální policie a vyšetřování</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

ISBN

979-8-3315-4364-8

ISSN

1063-6919

e-ISSN

2575-7075

Počet stran výsledku

10

Strana od-do

27124-27133

Název nakladatele

IEEE Computer Society

Místo vydání

Los Alamitos

Místo konání akce

Nashville

Datum konání akce

11. 6. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001601181100288