4 papers
OctoT2I: A Self-Evolving Agentic Text-to-Image Router
Xu Jiang, Bin Chen, Gehui Li +3
The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns from single-model scaling. Agen…
OSMamba: Omnidirectional Spectral Mamba with Dual-Domain Prior Generator for Exposure Correction
Gehui Li, Bin Chen, Chen Zhao +2
Exposure correction is a fundamental problem in computer vision and image processing. Recently, frequency domain-based methods have achieved impressive improvement, yet they still…
Multi-Agent Image Restoration
Xu Jiang, Gehui Li, Bin Chen +1
Image restoration (IR) is challenging due to the complexity of real-world degradations. While many specialized and all-in-one IR models have been developed, they fail to effectivel…
Adversarial Diffusion Compression for Real-World Image Super-Resolution
Bin Chen, Gehui Li, Rongyuan Wu +4
Real-world image super-resolution (Real-ISR) aims to reconstruct high-resolution images from low-resolution inputs degraded by complex, unknown processes. While many Stable Diffusi…