In this work, we observe that the generators, which are pre-trained on massive natural images, inherently hold the promising potential for superior low-light image enhancement against varying scenarios.Specifically, we embed a pre-trained generator to Retinex model to produce reflectance maps with enhanced detail and vividness, thereby recovering features degraded by low-light conditions.Taking one step further, we introduce a novel optimization strategy, which backpropagates the gradients to the input seeds rather than the parameters of the low-light enhancement model, thus intactly retaining the generative knowledge learned from natural images and achieving faster convergence speed. Benefiting from the pre-trained knowledge and seed-optimization strategy, the low-light enhancement model can significantly regularize the realness and fidelity of the enhanced result, thus rapidly generating high-quality images without training on any low-light dataset. Extensive experiments on various benchmarks demonstrate the superiority of the proposed method over numerous state-of-the-art methods qualitatively and quantitatively.
@article{arxiv.2402.09694,
title = {Seed Optimization with Frozen Generator for Superior Zero-shot Low-light Enhancement},
author = {Yuxuan Gu and Yi Jin and Ben Wang and Zhixiang Wei and Xiaoxiao Ma and Pengyang Ling and Haoxuan Wang and Huaian Chen and Enhong Chen},
journal= {arXiv preprint arXiv:2402.09694},
year = {2024}
}