Exposure Completing for Temporally Consistent Neural High Dynamic Range Video Rendering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929448587100160 |
|---|---|
| author | Cui, Jiahao Jiang, Wei Peng, Zhan Pan, Zhiyu Cao, Zhiguo |
| author_facet | Cui, Jiahao Jiang, Wei Peng, Zhan Pan, Zhiyu Cao, Zhiguo |
| contents | High dynamic range (HDR) video rendering from low dynamic range (LDR) videos where frames are of alternate exposure encounters significant challenges, due to the exposure change and absence at each time stamp. The exposure change and absence make existing methods generate flickering HDR results. In this paper, we propose a novel paradigm to render HDR frames via completing the absent exposure information, hence the exposure information is complete and consistent. Our approach involves interpolating neighbor LDR frames in the time dimension to reconstruct LDR frames for the absent exposures. Combining the interpolated and given LDR frames, the complete set of exposure information is available at each time stamp. This benefits the fusing process for HDR results, reducing noise and ghosting artifacts therefore improving temporal consistency. Extensive experimental evaluations on standard benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting the importance of absent exposure completing in HDR video rendering. The code is available at https://github.com/cuijiahao666/NECHDR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_13309 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exposure Completing for Temporally Consistent Neural High Dynamic Range Video Rendering Cui, Jiahao Jiang, Wei Peng, Zhan Pan, Zhiyu Cao, Zhiguo Computer Vision and Pattern Recognition Multimedia High dynamic range (HDR) video rendering from low dynamic range (LDR) videos where frames are of alternate exposure encounters significant challenges, due to the exposure change and absence at each time stamp. The exposure change and absence make existing methods generate flickering HDR results. In this paper, we propose a novel paradigm to render HDR frames via completing the absent exposure information, hence the exposure information is complete and consistent. Our approach involves interpolating neighbor LDR frames in the time dimension to reconstruct LDR frames for the absent exposures. Combining the interpolated and given LDR frames, the complete set of exposure information is available at each time stamp. This benefits the fusing process for HDR results, reducing noise and ghosting artifacts therefore improving temporal consistency. Extensive experimental evaluations on standard benchmarks demonstrate that our method achieves state-of-the-art performance, highlighting the importance of absent exposure completing in HDR video rendering. The code is available at https://github.com/cuijiahao666/NECHDR. |
| title | Exposure Completing for Temporally Consistent Neural High Dynamic Range Video Rendering |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2407.13309 |