Show simple item record

dc.contributor.authorDang, Bowenen_US
dc.contributor.authorZhao, Xien_US
dc.contributor.authorZhang, Bowenen_US
dc.contributor.authorWang, Heen_US
dc.contributor.editorChaine, Raphaëlleen_US
dc.contributor.editorDeng, Zhigangen_US
dc.contributor.editorKim, Min H.en_US
dc.date.accessioned2023-10-09T07:38:27Z
dc.date.available2023-10-09T07:38:27Z
dc.date.issued2023
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14982
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14982
dc.description.abstractWe propose a new method to reconstruct the 3D human body from RGB-D images with occlusions. The foremost challenge is the incompleteness of the RGB-D data due to occlusions between the body and the environment, leading to implausible reconstructions that suffer from severe human-scene penetration. To reconstruct a semantically and physically plausible human body, we propose to reduce the solution space based on scene information and prior knowledge. Our key idea is to constrain the solution space of the human body by considering the occluded body parts and visible body parts separately: modeling all plausible poses where the occluded body parts do not penetrate the scene, and constraining the visible body parts using depth data. Specifically, the first component is realized by a neural network that estimates the candidate region named the "free zone", a region carved out of the open space within which it is safe to search for poses of the invisible body parts without concern for penetration. The second component constrains the visible body parts using the "truncated shadow volume" of the scanned body point cloud. Furthermore, we propose to use a volume matching strategy, which yields better performance than surface matching, to match the human body with the confined region. We conducted experiments on the PROX dataset, and the results demonstrate that our method produces more accurate and plausible results compared with other methods.en_US
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectCCS Concepts: Computing methodologies -> Shape modeling; Reconstruction
dc.subjectComputing methodologies
dc.subjectShape modeling
dc.subjectReconstruction
dc.titleReconstructing 3D Human Pose from RGB-D Data with Occlusionsen_US
dc.description.seriesinformationComputer Graphics Forum
dc.description.sectionheadersRadiance and Appearance
dc.description.volume42
dc.description.number7
dc.identifier.doi10.1111/cgf.14982
dc.identifier.pages13 pages


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • 42-Issue 7
    Pacific Graphics 2023 - Symposium Proceedings

Show simple item record