WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structures
Quick Answer
This paper shows that The WREN neural network employs double U-Net-like structures for low light image enhancement, effectively addressing the instability of existing retinex-based methods.
Quick Take
By decomposing images into reflectance and illumination maps and enhancing the latter with a Transformer block, WREN achieves state-of-the-art performance across multiple datasets, demonstrating robustness against varying illumination conditions.
Key Points
- WREN uses a double U-Net-like structure for robust low light image enhancement.
- It decomposes images into reflectance and illumination maps, enhancing the illumination map.
- The model incorporates a Transformer block for improved illumination processing.
- WREN achieves state-of-the-art results across multiple datasets.
- The network is trained with a scale-invariant loss function for robustness.
DeepSignal Analysis
What happened
The WREN neural network introduces a novel approach for low light image enhancement by utilizing double U-Net-like structures. This method aims to improve the stability of retinex-based techniques, which often struggle with image decomposition under varying lighting conditions.
Key evidence
- WREN employs two U-Net-like sub-networks, where the first decomposes images into reflectance and illumination maps, addressing the instability of existing methods.
- The second sub-network enhances the illumination map using a customized Transformer block, adhering to the principles of retinex theory.
- Numerical results indicate that WREN achieves state-of-the-art performance across multiple datasets, showcasing its robustness against different illumination conditions.
Why it matters
The development of WREN is significant as it addresses a common limitation in low light image enhancement, where existing methods often lead to over-enhancement due to unstable decompositions. By improving the reliability of image enhancement in diverse lighting scenarios, WREN could have practical applications in fields such as photography, surveillance, and autonomous driving.
Paper Resources
📖 Reader Mode
~2 min readAbstract:This paper proposes a neural network for low light image enhancement (LLIE) based on retinex theory to make LLIE robust for various dynamic range scenes. The retinex theory is an image formulation model inspired by a human color perception hypothesis, where a low light image is decomposed into intrinsic color context (i.e., reflectance map) and scene-dependent illumination (i.e., illumination map). Due to non-uniqueness of its decomposition, existing retinex-based LLIE methods often fail to achieve stable decomposition, which lead to over-enhancement. Typically, they are sensitive to the dynamic ranges that vary in different lighting conditions. To tackle this issue, we propose WREN: An LLIE neural network with double U-Net-like structures. WREN consists of two U-Net-like sub-networks. The first network has one encoder and two decoders that decompose an input image into the reflectance and illumination maps. The second network with a customized Transformer block between an encoder and a decoder only enhances the illumination map obtained from the first network: This completely follows the assumption of the retinex theory. Finally, the enhanced illumination map is recombined with the reflectance map. The network is trained end-to-end with a scale-invariant loss function, which gives robustness against the illumination scaling. Numerical results show that our method achieves the state-of-the-art performance across multiple datasets. Our code is available online.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2607.15604 [cs.CV] |
| (or arXiv:2607.15604v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2607.15604 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Reina Kaneko [view email]
[v1]
Fri, 17 Jul 2026 03:56:28 UTC (9,150 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.