ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks
- Xintao Wang, Ke Yu, Xiaoou Tang
- Computer ScienceECCV Workshops
- 1 September 2018
This work thoroughly study three key components of SRGAN – network architecture, adversarial loss and perceptual loss, and improves each of them to derive an Enhanced SRGAN (ESRGAN), which achieves consistently better visual quality with more realistic and natural textures than SRGAN.
Interpreting the Latent Space of GANs for Semantic Face Editing
- Yujun Shen, Jinjin Gu, Xiaoou Tang, Bolei Zhou
- Computer ScienceComputer Vision and Pattern Recognition
- 25 July 2019
This work proposes a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs, and finds that the latent code of well-trained generative models actually learns a disentangled representation after linear transformations.
Blind Super-Resolution With Iterative Kernel Correction
- Jinjin Gu, Hannan Lu, W. Zuo, Chao Dong
- Computer ScienceComputer Vision and Pattern Recognition
- 6 April 2019
An iterative correction scheme -- IKC that achieves better results than direct kernel estimation in blind SR problem and an effective SR network architecture using spatial feature transform (SFT) layers to handle multiple blur kernels, named SFTMD.
PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration
- Jinjin Gu, Haoming Cai, Haoyu Chen, Xiaoxing Ye, Jimmy S. J. Ren, Chao Dong
- Computer ScienceEuropean Conference on Computer Vision
- 23 July 2020
It is indicated that existing IQA methods cannot fairly evaluate GAN-based IR algorithms, and a large-scale IQA dataset, called Perceptual Image Processing Algorithms (PIPAL) is contributed, which includes the results of GAn-based methods, which are missing in previous datasets.
Image Processing Using Multi-Code GAN Prior
- Jinjin Gu, Yujun Shen, Bolei Zhou
- Computer ScienceComputer Vision and Pattern Recognition
- 15 December 2019
A novel approach is proposed, called mGANprior, to incorporate the well-trained GANs as effective prior to a variety of image processing tasks, by employing multiple latent codes to generate multiple feature maps at some intermediate layer of the generator and composing them with adaptive channel importance to recover the input image.
Interpreting Super-Resolution Networks with Local Attribution Maps
This work proposes a novel attribution approach called local attribution map (LAM), which inherits the integral gradient method yet with two unique features: one is to use the blurred image as the baseline input, and the other is to adopt the progressive blurring function as the path function.
Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric
- Jinjin Gu, Haoming Cai, Haoyu Chen, Xiaoxing Ye, Jimmy S. J. Ren, Chao Dong
- Computer SciencearXiv.org
- 30 November 2020
Inspired by the find that the existing IQA methods have an unsatisfactory performance on the GAN-based distortion partially because of their low tolerance to spatial misalignment, a novel Space Warping Difference Network is proposed, which includes the novel l_2 pooling layers and Space Warped Difference layers.
NTIRE 2019 Challenge on Real Image Super-Resolution: Methods and Results
- Jianrui Cai, Shuhang Gu, Peidong He
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 1 June 2019
The 3rd NTIRE challenge on single-image super-resolution (restoration of rich details in a low-resolution image) is reviewed with a focus on proposed solutions and results and the state-of-the-art in real-world single image super- resolution.
Blind Image Super-Resolution: A Survey and Beyond
- Anran Liu, Yihao Liu, Jinjin Gu, Y. Qiao, Chao Dong
- Computer ScienceIEEE Transactions on Pattern Analysis and Machine…
- 7 July 2021
A taxonomy to categorize existing methods into three different classes according to their ways of degradation modelling and the data used to solve the SR model is proposed, which helps summarize and distinguish among existing methods.
Attention in Attention Network for Image Super-Resolution
- Haoyu Chen, Jinjin Gu, Zhi Zhang
- Computer SciencearXiv.org
- 19 April 2021
This work attempts to quantify and visualize attention mechanisms in SISR and shows that not all attention modules are equally beneficial and proposes attention in attention network (A$^2$N), which could achieve superior trade-off performances comparing with state-of-the-art networks of similar sizes.
...
...