OaIF: Occlusion‐Aware Implicit Function for Clothed Human Re‐construction

dc.contributor.authorTan, Yudien_US
dc.contributor.authorGuan, Boliangen_US
dc.contributor.authorZhou, Fanen_US
dc.contributor.authorSu, Zhuoen_US
dc.contributor.editorHauser, Helwig and Alliez, Pierreen_US
dc.date.accessioned2023-10-06T11:58:53Z
dc.date.available2023-10-06T11:58:53Z
dc.date.issued2023
dc.description.abstractClothed human re‐construction from a monocular image is challenging due to occlusion, depth‐ambiguity and variations of body poses. Recently, shape representation based on an implicit function, compared to explicit representation such as mesh and voxel, is more capable with complex topology of clothed human. This is mainly achieved by using pixel‐aligned features, facilitating implicit function to capture local details. But such methods utilize an identical feature map for all sampled points to get local features, making their models occlusion‐agnostic in the encoding stage. The decoder, as implicit function, only maps features and does not take occlusion into account explicitly. Thus, these methods fail to generalize well in poses with severe self‐occlusion. To address this, we present OaIF to encode local features conditioned in visibility of SMPL vertices. OaIF projects SMPL vertices onto image plane to obtain image features masked by visibility. Vertices features integrated with geometry information of mesh are then feed into a GAT network to encode jointly. We query hybrid features and occlusion factors for points through cross attention and learn occupancy fields for clothed human. The experiments demonstrate that OaIF achieves more robust and accurate re‐construction than the state of the art on both public datasets and wild images.en_US
dc.description.number6
dc.description.sectionheadersORIGINAL ARTICLES
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume42
dc.identifier.doi10.1111/cgf.14798
dc.identifier.issn1467-8659
dc.identifier.urihttps://doi.org/10.1111/cgf.14798
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14798
dc.publisher© 2023 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.subjectmodelling
dc.subjectimage‐based modelling
dc.subjectimplicit surfaces
dc.titleOaIF: Occlusion‐Aware Implicit Function for Clothed Human Re‐constructionen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
v42i6_27_14798.pdf
Size:
5.78 MB
Format:
Adobe Portable Document Format
Collections