← Search

Ruofan Zhang

2 accepted papers

2023

Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution

ICML 2023poster

Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range degradations to enhance generalization, a decline in accuracy…

Cited by 24SourcePDFScholar
2022

Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images

ECCV 2022poster

"Rendering high-resolution (HR) graphics brings substantial computational costs. Efficient graphics super-resolution (SR) methods may achieve HR rendering with small computing resources and have attracted extensive research interests in industry and research communities. We present a new method for…

Cited by 7SourcePDFScholar