Abstract | ||
---|---|---|
We present an information-theoretic regularization technique for few-shot novel view synthesis based on neural im-plicit representation. The proposed approach minimizes potential reconstruction inconsistency that happens due to in-sufficient viewpoints by imposing the entropy constraint of the density in each ray. In addition, to alleviate the poten-tial degenerate issue when all training images are acquired from almost redundant viewpoints, we further incorporate the spatial smoothness constraint into the estimated images by restricting information gains from additional rays with slightly different viewpoints. The main idea of our algorithm is to make reconstructed scenes compact along indi-vidual rays and consistent across rays in the neighborhood. The proposed regularizers can be plugged into most of existing neural volume rendering techniques based on NeRF in a straightforward way. Despite its simplicity, we achieve con-sistently improved performance compared to existing neural view synthesis methods by large margins on multiple stan-dard benchmarks. Our codes and models are available in the project website 1 1 http://cvlab.snu.ac.kr/research/InfoNeRF. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1109/CVPR52688.2022.01257 | IEEE Conference on Computer Vision and Pattern Recognition |
Keywords | DocType | Volume |
3D from multi-view and sensors, Image and video synthesis and generation, Low-level vision, Vision + graphics | Conference | 2022 |
Issue | Citations | PageRank |
1 | 0 | 0.34 |
References | Authors | |
0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mijeong Kim | 1 | 0 | 0.34 |
Seonguk Seo | 2 | 18 | 1.95 |
Bohyung Han | 3 | 2203 | 94.45 |