Abstract | ||
---|---|---|
One major challenge in 3D reconstruction is to infer the complete shape geometry from partial foreground occlusions. In this paper, we propose a method to reconstruct the complete 3D shape of an object from a single RGB image, with robustness to occlusion. Given the image and a silhouette of the visible region, our approach completes the silhouette of the occluded region and then generates a point cloud. We show improvements for reconstruction of non-occluded and partially occluded objects by providing the predicted complete silhouette as guidance. We also improve state-of-the-art for 3D shape prediction with a 2D reprojection loss from multiple synthetic views and a surface-based smoothing and refinement step. Experiments demonstrate the efficacy of our approach both quantitatively and qualitatively on synthetic and real scene datasets. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/WACV45572.2020.9093611 | 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) |
Keywords | DocType | ISSN |
3D shape prediction,silhouette guided point cloud reconstruction,shape geometry,partial foreground occlusions,RGB image | Conference | 2472-6737 |
ISBN | Citations | PageRank |
978-1-7281-6554-7 | 0 | 0.34 |
References | Authors | |
14 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Chuhang Zou | 1 | 10 | 1.24 |
Derek Hoiem | 2 | 4998 | 302.66 |