Super Resolution
Super-resolution (SR) aims to enhance the resolution of images or other data, improving detail and clarity from lower-resolution inputs. Current research focuses on developing efficient and effective SR models, employing various architectures such as convolutional neural networks, transformers, and diffusion models, often incorporating techniques like self-supervised learning and multi-scale processing to improve performance and reduce computational cost. These advancements have significant implications across diverse fields, including medical imaging (improving diagnostic accuracy), remote sensing (enhancing spatial detail), and computer vision (improving the quality of generated images and videos). The development of robust and efficient SR methods is crucial for numerous applications where high-resolution data is desirable but acquisition is costly or impractical.
Papers
Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection
Ziteng Cui, Yingying Zhu, Lin Gu, Guo-Jun Qi, Xiaoxiao Li, Renrui Zhang, Zenghui Zhang, Tatsuya Harada
Rethinking Degradation: Radiograph Super-Resolution via AID-SRGAN
Yongsong Huang, Qingzhong Wang, Shinichiro Omachi
Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution
Yushu Wu, Yifan Gong, Pu Zhao, Yanyu Li, Zheng Zhan, Wei Niu, Hao Tang, Minghai Qin, Bin Ren, Yanzhi Wang
Learning Generalizable Latent Representations for Novel Degradations in Super Resolution
Fengjun Li, Xin Feng, Fanglin Chen, Guangming Lu, Wenjie Pei
Sub-Aperture Feature Adaptation in Single Image Super-resolution Model for Light Field Imaging
Aupendu Kar, Suresh Nehra, Jayanta Mukhopadhyay, Prabir Kumar Biswas
Sparse-based Domain Adaptation Network for OCTA Image Super-Resolution Reconstruction
Huaying Hao, Cong Xu, Dan Zhang, Qifeng Yan, Jiong Zhang, Yue Liu, Yitian Zhao