activity
20152023
most citedReal-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data

85 citations · 679 across the 51 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

11 papers · 2 filters

cs.CV2021★ 3 cited

Reflash Dropout in Image Super-Resolution

Xiangtao Kong, Xina Liu, Jinjin Gu +2

Dropout is designed to relieve the overfitting problem in high-level vision tasks but is rarely applied in low-level vision tasks, like image super-resolution (SR). As a classic re…

cs.CV2021

Semantic-Sparse Colorization Network for Deep Exemplar-based Colorization

Yunpeng Bai, Chao Dong, Zenghao Chai +3

Exemplar-based colorization approaches rely on reference image to provide plausible colors for target gray-scale image. The key and difficulty of exemplar-based colorization is to…

cs.CV2021

Few-shot learning with improved local representations via bias rectify module

Chao Dong, Qi Ye, Wenchao Meng +1

Recent approaches based on metric learning have achieved great progress in few-shot learning. However, most of them are limited to image-level representation manners, which fail to…

cs.CV2021★ 26 cited

Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning

Yihao Liu, Hengyuan Zhao, Kelvin C. K. Chan +4

Video colorization is a challenging and highly ill-posed problem. Although recent years have witnessed remarkable progress in single image colorization, there is relatively less re…

cs.CV2021★ 2 cited

Finding Discriminative Filters for Specific Degradations in Blind Super-Resolution

Liangbin Xie, Xintao Wang, Chao Dong +2

Recent blind super-resolution (SR) methods typically consist of two branches, one for degradation prediction and the other for conditional restoration. However, our experiments sho…

cs.CV2021

Discovering Distinctive "Semantics" in Super-Resolution Networks

Yihao Liu, Anran Liu, Jinjin Gu +4

Image super-resolution (SR) is a representative low-level vision problem. Although deep SR networks have achieved extraordinary success, we are still unaware of their working mecha…