Author

Shigui Li

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Dec 2025

Consist-Retinex: One-Step Noise-Emphasized Consistency Training Accelerates High-Quality Retinex Enhancement

Consist-Retinex is proposed, which first uses a Retinex Transformer Decomposition Network to obtain paired reflectance and illumination maps, then trains two conditional consistency models with a Retinex-aware dual objective and adaptive noise-emphasized fixed-point sampling.

Jian Xu, Wei Chen, Shigui Li et al. · arXiv.org · 0 citations