Learning Self-Shadowing for Clothed Human Bodies
| dc.contributor.author | Einabadi, Farshad | en_US |
| dc.contributor.author | Guillemaut, Jean-Yves | en_US |
| dc.contributor.author | Hilton, Adrian | en_US |
| dc.contributor.editor | Haines, Eric | en_US |
| dc.contributor.editor | Garces, Elena | en_US |
| dc.date.accessioned | 2024-06-25T11:06:10Z | |
| dc.date.available | 2024-06-25T11:06:10Z | |
| dc.date.issued | 2024 | |
| dc.description.abstract | This paper proposes to learn self-shadowing on full-body, clothed human postures from monocular colour image input, by supervising a deep neural model. The proposed approach implicitly learns the articulated body shape in order to generate self-shadow maps without seeking to reconstruct explicitly or estimate parametric 3D body geometry. Furthermore, it is generalisable to different people without per-subject pre-training, and has fast inference timings. The proposed neural model is trained on self-shadow maps rendered from 3D scans of real people for various light directions. Inference of shadow maps for a given illumination is performed from only 2D image input. Quantitative and qualitative experiments demonstrate comparable results to the state of the art whilst being monocular and achieving a considerably faster inference time. We provide ablations of our methodology and further show how the inferred self-shadow maps can benefit monocular full-body human relighting. | en_US |
| dc.description.sectionheaders | Shadows | |
| dc.description.seriesinformation | Eurographics Symposium on Rendering | |
| dc.identifier.doi | 10.2312/sr.20241159 | |
| dc.identifier.isbn | 978-3-03868-262-2 | |
| dc.identifier.issn | 1727-3463 | |
| dc.identifier.pages | 7 pages | |
| dc.identifier.uri | https://doi.org/10.2312/sr.20241159 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.2312/sr20241159 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies -> Image-based rendering; Visibility; Neural networks | |
| dc.subject | CCS Concepts | |
| dc.subject | Computing methodologies | |
| dc.subject | > Image | |
| dc.subject | based rendering | |
| dc.subject | Visibility | |
| dc.subject | Neural networks | |
| dc.title | Learning Self-Shadowing for Clothed Human Bodies | en_US |