PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth
Many models have been proposed to estimate human pose and segmentation by leveraging information from several sources. A standard approach is to formulate it in a dual decomposition framework. However, these models generally suffer from the problem of high computational complexity. In this work, we...
| Main Authors: | , , , |
|---|---|
| Format: | Conference item |
| Language: | English |
| Published: |
Springer
2013
|
| _version_ | 1817930801263673344 |
|---|---|
| author | Vineet, V Sheasby, G Warrell, J Torr, PHS |
| author_facet | Vineet, V Sheasby, G Warrell, J Torr, PHS |
| author_sort | Vineet, V |
| collection | OXFORD |
| description | Many models have been proposed to estimate human pose and segmentation by leveraging information from several sources. A standard approach is to formulate it in a dual decomposition framework. However, these models generally suffer from the problem of high computational complexity. In this work, we propose PoseField, a new highly efficient filter-based mean-field inference approach for jointly estimating human segmentation, pose, per-pixel body parts, and depth given stereo pairs of images. We extensively evaluate the efficiency and accuracy offered by our approach on H2View [1], and Buffy [2] datasets. We achieve 20 to 70 times speedup compared to the current state-of-the-art methods, as well as achieving better accuracy in all these cases. |
| first_indexed | 2024-12-09T03:11:54Z |
| format | Conference item |
| id | oxford-uuid:7ee6801e-3602-4c2f-8ff5-09aa0a9c8efe |
| institution | University of Oxford |
| language | English |
| last_indexed | 2024-12-09T03:11:54Z |
| publishDate | 2013 |
| publisher | Springer |
| record_format | dspace |
| spelling | oxford-uuid:7ee6801e-3602-4c2f-8ff5-09aa0a9c8efe2024-10-11T12:47:39ZPoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depthConference itemhttp://purl.org/coar/resource_type/c_5794uuid:7ee6801e-3602-4c2f-8ff5-09aa0a9c8efeEnglishSymplectic ElementsSpringer2013Vineet, VSheasby, GWarrell, JTorr, PHSMany models have been proposed to estimate human pose and segmentation by leveraging information from several sources. A standard approach is to formulate it in a dual decomposition framework. However, these models generally suffer from the problem of high computational complexity. In this work, we propose PoseField, a new highly efficient filter-based mean-field inference approach for jointly estimating human segmentation, pose, per-pixel body parts, and depth given stereo pairs of images. We extensively evaluate the efficiency and accuracy offered by our approach on H2View [1], and Buffy [2] datasets. We achieve 20 to 70 times speedup compared to the current state-of-the-art methods, as well as achieving better accuracy in all these cases. |
| spellingShingle | Vineet, V Sheasby, G Warrell, J Torr, PHS PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth |
| title | PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth |
| title_full | PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth |
| title_fullStr | PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth |
| title_full_unstemmed | PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth |
| title_short | PoseField: an efficient mean-field based method for joint estimation of human pose, segmentation, and depth |
| title_sort | posefield an efficient mean field based method for joint estimation of human pose segmentation and depth |
| work_keys_str_mv | AT vineetv posefieldanefficientmeanfieldbasedmethodforjointestimationofhumanposesegmentationanddepth AT sheasbyg posefieldanefficientmeanfieldbasedmethodforjointestimationofhumanposesegmentationanddepth AT warrellj posefieldanefficientmeanfieldbasedmethodforjointestimationofhumanposesegmentationanddepth AT torrphs posefieldanefficientmeanfieldbasedmethodforjointestimationofhumanposesegmentationanddepth |