Name
Abstract | ||
|---|---|---|
This paper studies the problem of panoramic image reflection removal, aiming at reliving the content ambiguity between reflection and transmission scenes. Although a partial view of the reflection scene is included in the panoramic image, it cannot be utilized directly due to its misalignment with the reflection-contaminated image. We propose a two-step approach to solve this problem, by first accomplishing geometric and photometric alignment for the reflection scene via a coarse-to-fine strategy, and then restoring the transmission scene via a recovery network. The proposed method is trained with a synthetic dataset and verified quantitatively with a real panoramic image dataset. The effectiveness of the proposed method is validated by the significant performance advantage over single image-based reflection removal methods and generalization capacity to limited-FoV scenarios captured by conventional camera or mobile phone users. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1109/CVPR46437.2021.00767 | 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 |
DocType | ISSN | Citations |
Conference | 1063-6919 | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yuchen Hong | 1 | 0 | 0.34 |
| Qian Zheng | 2 | 44 | 13.91 |
| Lingran Zhao | 3 | 0 | 0.34 |
| Xudong Jiang | 4 | 1885 | 117.85 |
| Alex C. Kot | 5 | 1096 | 92.07 |
| Boxin Shi | 6 | 381 | 45.76 |