computer-vision-8
Blind Face Restoration
3260 papers • 126 benchmarks • 313 datasets
Blind face restoration aims at recovering high-quality faces from the low-quality counterparts suffering from unknown degradation, such as low-resolution, noise, blur, compression artifacts, etc. When applied to real-world scenarios, it becomes more challenging, due to more complicated degradation, diverse poses and expressions. Description source: Towards Real-World Blind Face Restoration with Generative Facial Prior Image source: Towards Real-World Blind Face Restoration with Generative Facial Prior
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in blind-face-restoration-8
Trend
Dataset
Best Model
Actions
CelebA-Test
CelebA-Test
LFW
LFW
WIDER
WIDER
Libraries
iUse these libraries to find blind-face-restoration-8 models and implementations
2 papers 649
Datasets
Subtasks
No subtasks available.
Most implemented papers
DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better
Zhangyang Wang, T. Martyniuk, Orest Kupyn, Junru Wu•Fri Aug 09 2019
It is demonstrated that DeblurGAN-V2 has very competitive performance on several popular benchmarks, in terms of deblurring quality (both objective and subjective), as well as efficiency, and is effective for general image restoration tasks too.
1050
