PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration

@inproceedings{Gu2020PIPALAL,
  title={PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration},
  author={Jinjin Gu and Haoming Cai and Haoyu Chen and Xiaoxing Ye and Jimmy S. J. Ren and Chao Dong},
  booktitle={ECCV},
  year={2020}
}
Image quality assessment (IQA) is the key factor for the fast development of image restoration (IR) algorithms. The most recent IR methods based on Generative Adversarial Networks (GANs) have achieved significant improvement in visual performance, but also presented great challenges for quantitative evaluation. Notably, we observe an increasing inconsistency between perceptual quality and the evaluation results. Then we raise two questions: (1) Can existing IQA methods objectively evaluate… Expand

Figures and Tables from this paper

Region-Adaptive Deformable Network for Image Quality Assessment
Quality Assessment of Super-Resolved Omnidirectional Image Quality Using Tangential Views
Designing a Practical Degradation Model for Deep Blind Image Super-Resolution
Interpreting Super-Resolution Networks with Local Attribution Maps
Perceptual Image Quality Assessment with Transformers
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
Debiased Subjective Assessment of Real-World Image Enhancement
Editorial: Introduction to the Issue on Deep Learning for Image/Video Restoration and Compression
...
1
2
...

References

SHOWING 1-10 OF 64 REFERENCES
The Perception-Distortion Tradeoff
EnhanceNet: Single Image Super-Resolution Through Automated Texture Synthesis
RankSRGAN: Generative Adversarial Networks With Ranker for Image Super-Resolution
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
  • C. Ledig, Lucas Theis, +6 authors W. Shi
  • Computer Science, Mathematics
  • 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2017
A Statistical Evaluation of Recent Full Reference Image Quality Assessment Algorithms
Making a “Completely Blind” Image Quality Analyzer
ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment
2018 PIRM Challenge on Perceptual Image Super-resolution
A Novel Image Quality Assessment With Globally and Locally Consilient Visual Quality Perception
...
1
2
3
4
5
...