Abstract | ||
---|---|---|
Synthesizing a novel view from different viewpoints has been an essential problem in 3D vision. Among a variety of view synthesis tasks, single image based view synthesis is particularly challenging. Recent works address this problem by a fixed number of image planes of discrete disparities, which tend to generate structurally inconsistent results on wide-baseline, scene-complicated datasets such as KITTI. In this paper, we propose the Self-Guided Elastic Displacement Network (SG-EDN), which explicitly models the geometric transformation by a novel non-discrete scene representation called layered displacement maps (LDM). To generate realistic views, we exploit the positional characteristics of the displacement maps and design a multi-scale structural pyramid for self-guided filtering on the displacement maps. To optimize efficiency and scene-adaptivity, we allow the effective range of each displacement map to be `elastic', with fully learnable parameters. Experimental results confirm that our framework outperforms existing methods in both quantitative and qualitative tests. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/WACV45572.2020.9093472 | 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) |
Keywords | DocType | ISSN |
image planes,discrete disparities,scene-complicated datasets,displacement map,multiscale structural pyramid,view synthesis tasks,single image based view synthesis,nondiscrete scene representation,elastic displacement network,3D vision,KITTI scene-complicated datasets,self-guided filtering,scene-adaptivity,quantitative tests,qualitative tests | Conference | 2472-6737 |
ISBN | Citations | PageRank |
978-1-7281-6554-7 | 1 | 0.35 |
References | Authors | |
17 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yicun Liu | 1 | 1 | 1.36 |
Jiawei Zhang | 2 | 111 | 11.52 |
Ye Ma | 3 | 1 | 0.35 |
Jimmy S. J. Ren | 4 | 324 | 23.85 |