ExposureDiffusion: Learning to Expose for Low-light Image Enhancement

by   Yufei Wang, et al.
Nanyang Technological University
The Hong Kong Polytechnic University

Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical distribution information, leading to visually undesirable results. This work addresses the issue by seamlessly integrating a diffusion model with a physics-based exposure model. Different from a vanilla diffusion model that has to perform Gaussian denoising, with the injected physics-based exposure model, our restoration process can directly start from a noisy image instead of pure noise. As such, our method obtains significantly improved performance and reduced inference time compared with vanilla diffusion models. To make full use of the advantages of different intermediate steps, we further propose an adaptive residual layer that effectively screens out the side-effect in the iterative refinement when the intermediate results have been already well-exposed. The proposed framework can work with both real-paired datasets, SOTA noise models, and different backbone networks. Note that, the proposed framework is compatible with real-paired datasets, real/synthetic noise models, and different backbone networks. We evaluate the proposed method on various public benchmarks, achieving promising results with consistent improvements using different exposure models and backbones. Besides, the proposed method achieves better generalization capacity for unseen amplifying ratios and better performance than a larger feedforward neural model when few parameters are adopted.


page 1

page 3

page 6

page 8


Learning an Adaptive Model for Extreme Low-light Raw Image Processing

Low-light images suffer from severe noise and low illumination. Current ...

Low-Light Image Enhancement with Normalizing Flow

To enhance low-light images to normally-exposed ones is highly ill-posed...

Low-Light Image Enhancement with Wavelet-based Diffusion Models

Diffusion models have achieved promising results in image restoration ta...

Learnability Enhancement for Low-light Raw Denoising: Where Paired Real Data Meets Noise Modeling

Low-light raw denoising is an important and valuable task in computation...

Recurrent Exposure Generation for Low-Light Face Detection

Face detection from low-light images is challenging due to limited photo...

Pyramid Diffusion Models For Low-light Image Enhancement

Recovering noise-covered details from low-light images is challenging, a...

PoGaIN: Poisson-Gaussian Image Noise Modeling from Paired Samples

Image noise can often be accurately fitted to a Poisson-Gaussian distrib...

Please sign up or login with your details

Forgot password? Click here to reset