Latent Feature-Guided Diffusion Models for Shadow Removal
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915280714727424 |
|---|---|
| author | Mei, Kangfu Figueroa, Luis Lin, Zhe Ding, Zhihong Cohen, Scott Patel, Vishal M. |
| author_facet | Mei, Kangfu Figueroa, Luis Lin, Zhe Ding, Zhihong Cohen, Scott Patel, Vishal M. |
| contents | Recovering textures under shadows has remained a challenging problem due to the difficulty of inferring shadow-free scenes from shadow images. In this paper, we propose the use of diffusion models as they offer a promising approach to gradually refine the details of shadow regions during the diffusion process. Our method improves this process by conditioning on a learned latent feature space that inherits the characteristics of shadow-free images, thus avoiding the limitation of conventional methods that condition on degraded images only. Additionally, we propose to alleviate potential local optima during training by fusing noise features with the diffusion network. We demonstrate the effectiveness of our approach which outperforms the previous best method by 13% in terms of RMSE on the AISTD dataset. Further, we explore instance-level shadow removal, where our model outperforms the previous best method by 82% in terms of RMSE on the DESOBA dataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_02156 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Latent Feature-Guided Diffusion Models for Shadow Removal Mei, Kangfu Figueroa, Luis Lin, Zhe Ding, Zhihong Cohen, Scott Patel, Vishal M. Computer Vision and Pattern Recognition Artificial Intelligence Recovering textures under shadows has remained a challenging problem due to the difficulty of inferring shadow-free scenes from shadow images. In this paper, we propose the use of diffusion models as they offer a promising approach to gradually refine the details of shadow regions during the diffusion process. Our method improves this process by conditioning on a learned latent feature space that inherits the characteristics of shadow-free images, thus avoiding the limitation of conventional methods that condition on degraded images only. Additionally, we propose to alleviate potential local optima during training by fusing noise features with the diffusion network. We demonstrate the effectiveness of our approach which outperforms the previous best method by 13% in terms of RMSE on the AISTD dataset. Further, we explore instance-level shadow removal, where our model outperforms the previous best method by 82% in terms of RMSE on the DESOBA dataset. |
| title | Latent Feature-Guided Diffusion Models for Shadow Removal |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2312.02156 |