Abstract
Diffusion models have achieved remarkable success in low-light image enhancement through Retinex-based decomposition, yet their requirement for hundreds of iterative sampling steps severely limits practical deployment. While recent consistency models offer promising one-step generation for \textit{unconditional synthesis}, their application to \textit{conditional enhancement} remains unexplored. We present \textbf{Consist-Retinex}, the first framework adapting consistency modeling to Retinex-based low-light enhancement. Our key insight is that conditional enhancement requires fundamentally different training dynamics than unconditional generation standard consistency training focuses on low-noise regions near the data manifold, while conditional mapping critically depends on large-noise regimes that bridge degraded inputs to enhanced outputs. We introduce two core innovations: (1) a \textbf{dual-objective consistency loss} combining temporal consistency with ground-truth alignment under randomized time sampling, providing full-spectrum supervision for stable convergence; and (2) an \textbf{adaptive noise-emphasized sampling strategy} that prioritizes training on large-noise regions essential for one-step conditional generation. On VE-LOL-L, Consist-Retinex achieves \textbf{state-of-the-art performance with single-step sampling} (\textbf{PSNR: 25.51 vs. 23.41, FID: 44.73 vs. 49.59} compared to Diff-Retinex++), while requiring only \textbf{1/8 of the training budget} relative to the 1000-step Diff-Retinex baseline.
Abstract (translated)
扩散模型在通过基于Retinex的分解进行低光图像增强方面取得了显著的成功，然而其需要数百次迭代采样步骤的要求严重限制了其实用部署。虽然最近的一致性模型为无条件合成提供了一步生成的有希望的方法，但它们在有条件增强方面的应用尚未被探索。我们提出了**Consist-Retinex**，这是第一个将一致性建模适应到基于Retinex的低光增强框架中的方法。 我们的关键见解是：与标准的一致性训练专注于数据流形附近的低噪声区域不同，条件映射的关键在于连接退化输入和增强输出的大噪声区域。为此，我们提出了两个核心创新： 1. **双目标一致性损失**：结合了时间一致性和在随机化时间采样下与真实标签对齐的损失函数，为稳定收敛提供了全面监督。 2. **自适应噪声强调采样策略**：优先训练对于一步条件生成至关重要的大噪声区域。 在VE-LOL-L数据集上，Consist-Retinex实现了单步采样的最先进的性能（与Diff-Retinex++相比，PSNR: 25.51 vs. 23.41, FID: 44.73 vs. 49.59），同时相对于需要1000步的Diff-Retinex基线，仅需**训练预算的八分之一**。
URL
https://arxiv.org/abs/2512.08982
