ESRGAN+ : Further Improving Enhanced Super-Resolution Generative Adversarial Network
arXiv:2001.08073 · doi:10.1109/ICASSP40776.2020.9054071
Abstract
Enhanced Super-Resolution Generative Adversarial Network (ESRGAN) is a perceptual-driven approach for single image super resolution that is able to produce photorealistic images. Despite the visual quality of these generated images, there is still room for improvement. In this fashion, the model is extended to further improve the perceptual quality of the images. We have designed a novel block to replace the one used by the original ESRGAN. Moreover, we introduce noise inputs to the generator network in order to exploit stochastic variation. The resulting images present more realistic textures. The code is available at https://github.com/ncarraz/ESRGANplus .
arXiv commentICASSP 2020
References in corpus (4)
Cited by in corpus (15)
- Light Field Image Super-Resolution Using Deformable Convolution
- PNEN: Pyramid Non-Local Enhanced Networks
- Conditional Hyper-Network for Blind Super-Resolution with Multiple Degradations
- Blind Motion Deblurring Super-Resolution: When Dynamic Spatio-Temporal Learning Meets Static Image Understanding
- Multi-Resolution Data Fusion for Super Resolution Imaging
- Distributed Learning and Inference with Compressed Images
- Unsupervised High-Resolution Portrait Gaze Correction and Animation
- Exploiting Digital Surface Models for Inferring Super-Resolution for Remotely Sensed Images
- StarSRGAN: Improving Real-World Blind Super-Resolution
- Variational AutoEncoder for Reference based Image Super-Resolution
- Noise Conditional Flow Model for Learning the Super-Resolution Space
- Joint Super-Resolution and Rectification for Solar Cell Inspection
- SDC-HSDD-NDSA: Structure Detecting Cluster by Hierarchical Secondary Directed Differential with Normalized Density and Self-Adaption
- ATP-Net: An Attention-based Ternary Projection Network For Compressed Sensing
- Debiased Subjective Assessment of Real-World Image Enhancement