Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.11874 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916272240852992 |
|---|---|
| author | Zhong, Haofeng Hong, Yuchen Weng, Shuchen Liang, Jinxiu Shi, Boxin |
| author_facet | Zhong, Haofeng Hong, Yuchen Weng, Shuchen Liang, Jinxiu Shi, Boxin |
| contents | This paper studies the problem of language-guided reflection separation, which aims at addressing the ill-posed reflection separation problem by introducing language descriptions to provide layer content. We propose a unified framework to solve this problem, which leverages the cross-attention mechanism with contrastive learning strategies to construct the correspondence between language descriptions and image layers. A gated network design and a randomized training strategy are employed to tackle the recognizable layer ambiguity. The effectiveness of the proposed method is validated by the significant performance advantage over existing reflection separation methods on both quantitative and qualitative comparisons. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_11874 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Language-guided Image Reflection Separation Zhong, Haofeng Hong, Yuchen Weng, Shuchen Liang, Jinxiu Shi, Boxin Computer Vision and Pattern Recognition This paper studies the problem of language-guided reflection separation, which aims at addressing the ill-posed reflection separation problem by introducing language descriptions to provide layer content. We propose a unified framework to solve this problem, which leverages the cross-attention mechanism with contrastive learning strategies to construct the correspondence between language descriptions and image layers. A gated network design and a randomized training strategy are employed to tackle the recognizable layer ambiguity. The effectiveness of the proposed method is validated by the significant performance advantage over existing reflection separation methods on both quantitative and qualitative comparisons. |
| title | Language-guided Image Reflection Separation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2402.11874 |