4 papers
Bridging Restoration and Generation in One-step Diffusion for Real-World Image Super-Resolution
Shyang-En Weng, Yi-Cheng Liao, Yu-Syuan Xu +3
Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR), but their iterative sampling is computationally prohibitive, driving efforts to distil…
The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview
Jiatong Li, Zheng Chen, Kai Liu +91
This paper provides a review of the NTIRE 2026 challenge on mobile real-world image super-resolution, highlighting the proposed solutions and the resulting outcomes. The challenge…
Learning Ordinal Degradation Representations with Textual Priors for Diffusion-Based Blind Image Super-Resolution
Yi-Cheng Liao, Shyang-En Weng, Yu-Syuan Xu +4
Blind image super-resolution (Blind SR) has achieved remarkable perceptual quality via generative priors. However, lacking clear degradation representations such as varying severit…
Rethinking Theoretical Illumination for Efficient Low-Light Image Enhancement
Shyang-En Weng, Cheng-Yen Hsiao, Li-Wei Lu +4
Enhancing low-light images remains a critical challenge in computer vision, as does designing lightweight models for edge devices that can handle the computational demands of deep…