Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929544180531200 |
|---|---|
| author | Wang, Zhouxia Zhang, Jiawei Wang, Xintao Chen, Tianshui Shan, Ying Wang, Wenping Luo, Ping |
| author_facet | Wang, Zhouxia Zhang, Jiawei Wang, Xintao Chen, Tianshui Shan, Ying Wang, Wenping Luo, Ping |
| contents | Recent progress in blind face restoration has resulted in producing high-quality restored results for static images. However, efforts to extend these advancements to video scenarios have been minimal, partly because of the absence of benchmarks that allow for a comprehensive and fair comparison. In this work, we first present a fair evaluation benchmark, in which we first introduce a Real-world Low-Quality Face Video benchmark (RFV-LQ), evaluate several leading image-based face restoration algorithms, and conduct a thorough systematical analysis of the benefits and challenges associated with extending blind face image restoration algorithms to degraded face videos. Our analysis identifies several key issues, primarily categorized into two aspects: significant jitters in facial components and noise-shape flickering between frames. To address these issues, we propose a Temporal Consistency Network (TCN) cooperated with alignment smoothing to reduce jitters and flickers in restored videos. TCN is a flexible component that can be seamlessly plugged into the most advanced face image restoration algorithms, ensuring the quality of image-based restoration is maintained as closely as possible. Extensive experiments have been conducted to evaluate the effectiveness and efficiency of our proposed TCN and alignment smoothing operation. Project page: https://wzhouxiff.github.io/projects/FIR2FVR/FIR2FVR. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_11828 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos Wang, Zhouxia Zhang, Jiawei Wang, Xintao Chen, Tianshui Shan, Ying Wang, Wenping Luo, Ping Computer Vision and Pattern Recognition Recent progress in blind face restoration has resulted in producing high-quality restored results for static images. However, efforts to extend these advancements to video scenarios have been minimal, partly because of the absence of benchmarks that allow for a comprehensive and fair comparison. In this work, we first present a fair evaluation benchmark, in which we first introduce a Real-world Low-Quality Face Video benchmark (RFV-LQ), evaluate several leading image-based face restoration algorithms, and conduct a thorough systematical analysis of the benefits and challenges associated with extending blind face image restoration algorithms to degraded face videos. Our analysis identifies several key issues, primarily categorized into two aspects: significant jitters in facial components and noise-shape flickering between frames. To address these issues, we propose a Temporal Consistency Network (TCN) cooperated with alignment smoothing to reduce jitters and flickers in restored videos. TCN is a flexible component that can be seamlessly plugged into the most advanced face image restoration algorithms, ensuring the quality of image-based restoration is maintained as closely as possible. Extensive experiments have been conducted to evaluate the effectiveness and efficiency of our proposed TCN and alignment smoothing operation. Project page: https://wzhouxiff.github.io/projects/FIR2FVR/FIR2FVR. |
| title | Analysis and Benchmarking of Extending Blind Face Image Restoration to Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.11828 |