SRFeat: Single Image Super-Resolution with Feature Discrimination

By Seong-Jin Park, Hyeongseok Son, Sunghyun Cho, Ki Sang Hong, Seungyong Lee. 2018

187 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Fahad Shahbaz Khan
2. Ming-Hsuan Yang
3. Salman Hameed Khan
4. Ling Shao
5. Luc Van Gool
6. Steven C. H. Hoi
7. Dacheng Tao
8. Munawar Hayat

In Media Technology

1. Salman Hameed Khan
2. Ming-Hsuan Yang
3. Fahad Shahbaz Khan
4. Munawar Hayat
5. Syed Waqas Zamir
6. Aditya Arora
7. Saeed Anwar
8. Nick Barnes

Citations in the corpus

• Transformers in Vision: A Survey (2021, methodology): “Further, perceptual SR approaches [112, 113, 153, 172, 214], in addition to per-pixel loss, employ adversarial loss [71] and perceptual loss [95] based on deep features extracted from pre-trained CNNs.”
• Learning Enriched Features for Real Image Restoration and Enhancement (2020, background): “Other networks designed to perform SR include recursive learning [57,41,3], progressive reconstruction [105,60], dense connections [99,104,127], attention mechanisms [125,23,126], multi-branch learning [60,66,22,64], and generative adversarial networks (GANs) [104,76,87,63].”
• A Deep Journey into Super-resolution (2019, methodology): “[85] is another GAN-based Super-Resolution algorithm with Feature Discrimination.”
• Densely Residual Laplacian Super-Resolution (2019, background): “The results of SRFeat [34] are perceptually better than [33].”
• Learning Enriched Features for Fast Image Restoration and Enhancement (2022, background): “…designed to perform SR include recursive learning [64], [65], [66], progressive reconstruction [67], [68], dense connections [7], [69], [70], attention mechanisms [71], [72], [73], multi-branch learning [68], [74], [75], [76], and generative adversarial networks (GANs) [70], [77], [78], [79].”
• Coherent Semantic Attention for Image Inpainting (2019, methodology): “Our feature patch discriminator combines the advantages of the conventional feature discriminator [25] and patch discriminator [17], which is not only fast and stable during training but also makes the refinement network synthesize more meaningful high-frequency details.”
• Deep Learning for Image Super-Resolution: A Survey (2019, background): “[133] argue that the pixel-level discriminator causes generating meaningless high-frequency noise, and attach another feature-level”