Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.03011 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915226569408512 |
|---|---|
| author | Wang, Junying Liu, Jingyuan Sun, Xin Singh, Krishna Kumar Shu, Zhixin Zhang, He Yang, Jimei Zhao, Nanxuan Wang, Tuanfeng Y. Chen, Simon S. Neumann, Ulrich Yoon, Jae Shin |
| author_facet | Wang, Junying Liu, Jingyuan Sun, Xin Singh, Krishna Kumar Shu, Zhixin Zhang, He Yang, Jimei Zhao, Nanxuan Wang, Tuanfeng Y. Chen, Simon S. Neumann, Ulrich Yoon, Jae Shin |
| contents | This paper introduces Comprehensive Relighting, the first all-in-one approach that can both control and harmonize the lighting from an image or video of humans with arbitrary body parts from any scene. Building such a generalizable model is extremely challenging due to the lack of dataset, restricting existing image-based relighting models to a specific scenario (e.g., face or static human). To address this challenge, we repurpose a pre-trained diffusion model as a general image prior and jointly model the human relighting and background harmonization in the coarse-to-fine framework. To further enhance the temporal coherence of the relighting, we introduce an unsupervised temporal lighting model that learns the lighting cycle consistency from many real-world videos without any ground truth. In inference time, our temporal lighting module is combined with the diffusion models through the spatio-temporal feature blending algorithms without extra training; and we apply a new guided refinement as a post-processing to preserve the high-frequency details from the input image. In the experiments, Comprehensive Relighting shows a strong generalizability and lighting temporal coherence, outperforming existing image-based human relighting and harmonization methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_03011 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization Wang, Junying Liu, Jingyuan Sun, Xin Singh, Krishna Kumar Shu, Zhixin Zhang, He Yang, Jimei Zhao, Nanxuan Wang, Tuanfeng Y. Chen, Simon S. Neumann, Ulrich Yoon, Jae Shin Computer Vision and Pattern Recognition This paper introduces Comprehensive Relighting, the first all-in-one approach that can both control and harmonize the lighting from an image or video of humans with arbitrary body parts from any scene. Building such a generalizable model is extremely challenging due to the lack of dataset, restricting existing image-based relighting models to a specific scenario (e.g., face or static human). To address this challenge, we repurpose a pre-trained diffusion model as a general image prior and jointly model the human relighting and background harmonization in the coarse-to-fine framework. To further enhance the temporal coherence of the relighting, we introduce an unsupervised temporal lighting model that learns the lighting cycle consistency from many real-world videos without any ground truth. In inference time, our temporal lighting module is combined with the diffusion models through the spatio-temporal feature blending algorithms without extra training; and we apply a new guided refinement as a post-processing to preserve the high-frequency details from the input image. In the experiments, Comprehensive Relighting shows a strong generalizability and lighting temporal coherence, outperforming existing image-based human relighting and harmonization methods. |
| title | Comprehensive Relighting: Generalizable and Consistent Monocular Human Relighting and Harmonization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.03011 |