9 papers
VICR: Visual In-Context Restoration for Real-World Image Super-Resolution
Qichang Zhang, Hailong Wang, Baiang Li +4
Real-world image super-resolution (Real-ISR) requires balancing structural fidelity to degraded observations with realistic detail synthesis. However, existing generative Real-ISR…
Lucky High Dynamic Range Smartphone Imaging
Baiang Li, Ruyu Yan, Ethan Tseng +4
While the human eye can perceive an impressive twenty stops of dynamic range, smartphone camera sensors remain limited to about twelve stops despite decades of research. A variety…
Weak-to-Strong Knowledge Distillation Accelerates Visual Learning
Baiang Li, Wenhao Chai, Felix Heide
Large-scale visual learning is increasingly limited by training cost. Existing knowledge distillation methods transfer from a stronger teacher to a weaker student for compression o…
The Fourth Challenge on Image Super-Resolution (4) at NTIRE 2026: Benchmark Results and Method Overview
Zheng Chen, Kai Liu, Jingkai Wang +150
This paper presents the NTIRE 2026 image super-resolution (4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to r…
Exploiting Regional Information Transformer for Single Image Deraining
Baiang Li, Zhao Zhang, Huan Zheng +5
Transformer-based Single Image Deraining (SID) methods have achieved remarkable success, primarily attributed to their robust capability in capturing long-range interactions. Howev…
Matting by Generation
Zhixiang Wang, Baiang Li, Jian Wang +4
This paper introduces an innovative approach for image matting that redefines the traditional regression-based task as a generative modeling challenge. Our method harnesses the cap…