Dual Associated Encoder for Face Restoration
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_ | 1866916099440771072 |
|---|---|
| author | Tsai, Yu-Ju Liu, Yu-Lun Qi, Lu Chan, Kelvin C. K. Yang, Ming-Hsuan |
| author_facet | Tsai, Yu-Ju Liu, Yu-Lun Qi, Lu Chan, Kelvin C. K. Yang, Ming-Hsuan |
| contents | Restoring facial details from low-quality (LQ) images has remained a challenging problem due to its ill-posedness induced by various degradations in the wild. The existing codebook prior mitigates the ill-posedness by leveraging an autoencoder and learned codebook of high-quality (HQ) features, achieving remarkable quality. However, existing approaches in this paradigm frequently depend on a single encoder pre-trained on HQ data for restoring HQ images, disregarding the domain gap between LQ and HQ images. As a result, the encoding of LQ inputs may be insufficient, resulting in suboptimal performance. To tackle this problem, we propose a novel dual-branch framework named DAEFR. Our method introduces an auxiliary LQ branch that extracts crucial information from the LQ inputs. Additionally, we incorporate association training to promote effective synergy between the two branches, enhancing code prediction and output quality. We evaluate the effectiveness of DAEFR on both synthetic and real-world datasets, demonstrating its superior performance in restoring facial details. Project page: https://liagm.github.io/DAEFR/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_07314 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Dual Associated Encoder for Face Restoration Tsai, Yu-Ju Liu, Yu-Lun Qi, Lu Chan, Kelvin C. K. Yang, Ming-Hsuan Computer Vision and Pattern Recognition Restoring facial details from low-quality (LQ) images has remained a challenging problem due to its ill-posedness induced by various degradations in the wild. The existing codebook prior mitigates the ill-posedness by leveraging an autoencoder and learned codebook of high-quality (HQ) features, achieving remarkable quality. However, existing approaches in this paradigm frequently depend on a single encoder pre-trained on HQ data for restoring HQ images, disregarding the domain gap between LQ and HQ images. As a result, the encoding of LQ inputs may be insufficient, resulting in suboptimal performance. To tackle this problem, we propose a novel dual-branch framework named DAEFR. Our method introduces an auxiliary LQ branch that extracts crucial information from the LQ inputs. Additionally, we incorporate association training to promote effective synergy between the two branches, enhancing code prediction and output quality. We evaluate the effectiveness of DAEFR on both synthetic and real-world datasets, demonstrating its superior performance in restoring facial details. Project page: https://liagm.github.io/DAEFR/ |
| title | Dual Associated Encoder for Face Restoration |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2308.07314 |