Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910871467327488 |
|---|---|
| author | Zhou, Yujie Bu, Jiazi Ling, Pengyang Zhang, Pan Wu, Tong Huang, Qidong Li, Jinsong Dong, Xiaoyi Zang, Yuhang Cao, Yuhang Rao, Anyi Wang, Jiaqi Niu, Li |
| author_facet | Zhou, Yujie Bu, Jiazi Ling, Pengyang Zhang, Pan Wu, Tong Huang, Qidong Li, Jinsong Dong, Xiaoyi Zang, Yuhang Cao, Yuhang Rao, Anyi Wang, Jiaqi Niu, Li |
| contents | Recent advancements in image relighting models, driven by large-scale datasets and pre-trained diffusion models, have enabled the imposition of consistent lighting. However, video relighting still lags, primarily due to the excessive training costs and the scarcity of diverse, high-quality video relighting datasets. A simple application of image relighting models on a frame-by-frame basis leads to several issues: lighting source inconsistency and relighted appearance inconsistency, resulting in flickers in the generated videos. In this work, we propose Light-A-Video, a training-free approach to achieve temporally smooth video relighting. Adapted from image relighting models, Light-A-Video introduces two key techniques to enhance lighting consistency. First, we design a Consistent Light Attention (CLA) module, which enhances cross-frame interactions within the self-attention layers of the image relight model to stabilize the generation of the background lighting source. Second, leveraging the physical principle of light transport independence, we apply linear blending between the source video's appearance and the relighted appearance, using a Progressive Light Fusion (PLF) strategy to ensure smooth temporal transitions in illumination. Experiments show that Light-A-Video improves the temporal consistency of relighted video while maintaining the relighted image quality, ensuring coherent lighting transitions across frames. Project page: https://bujiazi.github.io/light-a-video.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_08590 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Light-A-Video: Training-free Video Relighting via Progressive Light Fusion Zhou, Yujie Bu, Jiazi Ling, Pengyang Zhang, Pan Wu, Tong Huang, Qidong Li, Jinsong Dong, Xiaoyi Zang, Yuhang Cao, Yuhang Rao, Anyi Wang, Jiaqi Niu, Li Computer Vision and Pattern Recognition Recent advancements in image relighting models, driven by large-scale datasets and pre-trained diffusion models, have enabled the imposition of consistent lighting. However, video relighting still lags, primarily due to the excessive training costs and the scarcity of diverse, high-quality video relighting datasets. A simple application of image relighting models on a frame-by-frame basis leads to several issues: lighting source inconsistency and relighted appearance inconsistency, resulting in flickers in the generated videos. In this work, we propose Light-A-Video, a training-free approach to achieve temporally smooth video relighting. Adapted from image relighting models, Light-A-Video introduces two key techniques to enhance lighting consistency. First, we design a Consistent Light Attention (CLA) module, which enhances cross-frame interactions within the self-attention layers of the image relight model to stabilize the generation of the background lighting source. Second, leveraging the physical principle of light transport independence, we apply linear blending between the source video's appearance and the relighted appearance, using a Progressive Light Fusion (PLF) strategy to ensure smooth temporal transitions in illumination. Experiments show that Light-A-Video improves the temporal consistency of relighted video while maintaining the relighted image quality, ensuring coherent lighting transitions across frames. Project page: https://bujiazi.github.io/light-a-video.github.io/. |
| title | Light-A-Video: Training-free Video Relighting via Progressive Light Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.08590 |