DC Field | Value | Language |
---|---|---|
dc.contributor.author | Cho, Hanbyel | ko |
dc.contributor.author | Cho, Yooshin | ko |
dc.contributor.author | Yu, Jaemyung | ko |
dc.contributor.author | Kim, Junmo | ko |
dc.date.accessioned | 2022-11-21T02:00:39Z | - |
dc.date.available | 2022-11-21T02:00:39Z | - |
dc.date.created | 2022-11-19 | - |
dc.date.issued | 2021-10 | - |
dc.identifier.citation | 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021, pp.11149 - 11158 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10203/300180 | - |
dc.description.abstract | Existing 3D human pose estimation algorithms trained on distortion-free datasets suffer performance drop when applied to new scenarios with a specific camera distortion. In this paper, we propose a simple yet effective model for 3D human pose estimation in video that can quickly adapt to any distortion environment by utilizing MAML, a representative optimization-based meta-learning algorithm. We consider a sequence of 2D keypoints in a particular distortion as a single task of MAML. However, due to the absence of a large-scale dataset in a distorted environment, we propose an efficient method to generate synthetic distorted data from undistorted 2D keypoints. For the evaluation, we assume two practical testing situations depending on whether a motion capture sensor is available or not. In particular, we propose Inference Stage Optimization using bone-length symmetry and consistency. Extensive evaluation shows that our proposed method successfully adapts to various degrees of distortion in the testing phase and outperforms the existing state-of-the-art approaches. The proposed method is useful in practice because it does not require camera calibration and additional computations in a testing set-up. Code is available at https://github.com/hanbyel0105/CamDistHumanPose3D. | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning | - |
dc.type | Conference | - |
dc.identifier.scopusid | 2-s2.0-85127783118 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 11149 | - |
dc.citation.endingpage | 11158 | - |
dc.citation.publicationname | 18th IEEE/CVF International Conference on Computer Vision, ICCV 2021 | - |
dc.identifier.conferencecountry | CN | - |
dc.identifier.conferencelocation | Montreal, QC | - |
dc.identifier.doi | 10.1109/ICCV48922.2021.01098 | - |
dc.contributor.localauthor | Kim, Junmo | - |
dc.contributor.nonIdAuthor | Cho, Hanbyel | - |
dc.contributor.nonIdAuthor | Cho, Yooshin | - |
dc.contributor.nonIdAuthor | Yu, Jaemyung | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.