Wang, Hengyi;
Wang, Jingwen;
Agapito, Lourdes;
(2024)
MorpheuS: Neural Dynamic 360∘ Surface Reconstruction from Monocular RGB-D Video.
In:
2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).
(pp. pp. 20965-20976).
IEEE: Seattle, WA, USA.
Preview |
Text
Agapito_2312.00778v2.pdf - Accepted Version Download (17MB) | Preview |
Abstract
Neural rendering has demonstrated remarkable success in dynamic scene reconstruction. Thanks to the expressiveness of neural representations, prior works can accurately capture the motion and achieve high-fidelity reconstruction of the target object. Despite this, real-world video sce-narios often feature large unobserved regions where neural representations struggle to achieve realistic completion. To tackle this challenge, we introduce MorpheuS, a framework for dynamic 360∘ surface reconstruction from a casually captured RGB-D video. Our approach models the target scene as a canonical field that encodes its geometry and appearance, in conjunction with a defor-mation field that warps points from the current frame to the canonical space. We leverage a view-dependent diffusion prior and distill knowledge from it to achieve realistic completion of unobserved regions. Experimental results on various real-world and synthetic datasets show that our method can achieve high-fidelity 360° surface reconstruction of a deformable object from a monocular RGB-D video. Project page: https: / /hengyi wang. gi thub. io/ pro jects/morpheus.
| Type: | Proceedings paper |
|---|---|
| Title: | MorpheuS: Neural Dynamic 360∘ Surface Reconstruction from Monocular RGB-D Video |
| Event: | 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
| Dates: | 16 Jun 2024 - 22 Jun 2024 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/cvpr52733.2024.01981 |
| Publisher version: | https://doi.org/10.1109/cvpr52733.2024.01981 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Dynamic scene reconstruction, diffusion prior, neural field |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10204121 |
Loading...
Loading...Loading...| 1. |  United Kingdom | 4 |
| 2. |  Norway | 1 |
| 3. |  United States | 1 |
Archive Staff Only
 |
View Item |
