# Seed Optimization with Frozen Generator for Superior Zero-shot Low-light Enhancement

arXiv: https://arxiv.org/abs/2402.09694 · HTML: https://mlsanity.com/paper/2402.09694/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 43 references that are in the map.
- First posted on arXiv 15 Feb 2024.

## Builds on (most cited first, 28 of 28)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Generating Diverse High-Fidelity Images with VQ-VAE-2](https://mlsanity.com/paper/1906.00446/) (2019)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Retinex-inspired Unrolling with Cooperative Prior Architecture Search for Low-light Image Enhancement](https://mlsanity.com/paper/2012.05609/) (2020)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [Generative Diffusion Prior for Unified Image Restoration and Enhancement](https://mlsanity.com/paper/2304.01247/) (2023)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution](https://mlsanity.com/paper/2012.00739/) (2020)
- [Low-Light Image Enhancement with Wavelet-based Diffusion Models](https://mlsanity.com/paper/2306.00306/) (2023)
- [Iterative Prompt Learning for Unsupervised Backlit Image Enhancement](https://mlsanity.com/paper/2303.17569/) (2023)
- [Semantic Segmentation of Underwater Imagery: Dataset and Benchmark](https://mlsanity.com/paper/2004.01241/) (2020)
- [Implicit Neural Representation for Cooperative Low-light Image Enhancement](https://mlsanity.com/paper/2303.11722/) (2023)
- [RIDCP: Revitalizing Real Image Dehazing via High-Quality Codebook Priors](https://mlsanity.com/paper/2304.03994/) (2023)
- [Semantic-Guided Zero-Shot Learning for Low-Light Image/Video Enhancement](https://mlsanity.com/paper/2110.00970/) (2021)
- [Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement](https://mlsanity.com/paper/2110.00984/) (2021)
- [Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network](https://mlsanity.com/paper/2012.15020/) (2020)
- [EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANs](https://mlsanity.com/paper/2111.15097/) (2021)

## Abstract (arXiv)

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.