# Towards Scale-Aware Low-Light Enhancement via Structure-Guided Transformer Design

arXiv: https://arxiv.org/abs/2504.14075 · HTML: https://mlsanity.com/paper/2504.14075/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 75 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Builds on (most cited first, 30 of 34)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Deep Retinex Decomposition for Low-Light Enhancement](https://mlsanity.com/paper/1808.04560/) (2018)
- [Kindling the Darkness: A Practical Low-light Image Enhancer](https://mlsanity.com/paper/1905.04161/) (2019)
- [Learning Enriched Features for Real Image Restoration and Enhancement](https://mlsanity.com/paper/2003.06792/) (2020)
- [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023)
- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Deep Bilateral Learning for Real-Time Image Enhancement](https://mlsanity.com/paper/1707.02880/) (2017)
- [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021)
- [Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks](https://mlsanity.com/paper/1710.01992/) (2017)
- [Generative Adversarial Transformers](https://mlsanity.com/paper/2103.01209/) (2021)
- [StructureFlow: Image Inpainting via Structure-aware Appearance Flow](https://mlsanity.com/paper/1908.03852/) (2019)
- [Learning Warped Guidance for Blind Face Restoration](https://mlsanity.com/paper/1804.04829/) (2018)
- [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://mlsanity.com/paper/2209.11345/) (2022)
- [Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging](https://mlsanity.com/paper/2205.10102/) (2022)
- [Exemplar Guided Face Image Super-Resolution without Facial Landmarks](https://mlsanity.com/paper/1906.07078/) (2019)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Aesthetic-Driven Image Enhancement by Adversarial Learning](https://mlsanity.com/paper/1707.05251/) (2017)
- [GLARE: Low Light Image Enhancement via Generative Latent Feature based Codebook Retrieval](https://mlsanity.com/paper/2407.12431/) (2024)
- [Exposure: A White-Box Photo Post-Processing Framework](https://mlsanity.com/paper/1709.09602/) (2017)
- [NTIRE 2024 Challenge on Low Light Image Enhancement: Methods and Results](https://mlsanity.com/paper/2404.14248/) (2024)
- [NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results](https://mlsanity.com/paper/2504.12711/) (2025)
- [LITA-GS: Illumination-Agnostic Novel View Synthesis via Reference-Free 3D Gaussian Splatting and Physical Priors](https://mlsanity.com/paper/2504.00219/) (2025)
- [ShadowRefiner: Towards Mask-free Shadow Removal via Fast Fourier Transformer](https://mlsanity.com/paper/2406.02559/) (2024)

## Built on by (most cited first, 5 of 5)

- [Low Light Image Enhancement Challenge at NTIRE 2026](https://mlsanity.com/paper/2604.17669/) (2026)
- [RetinexDualV2: Physically-Grounded Dual Retinex for Generalized UHD Image Restoration](https://mlsanity.com/paper/2603.27979/) (2026)
- [HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing](https://mlsanity.com/paper/2604.03800/) (2026)
- [UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization](https://mlsanity.com/paper/2604.13383/) (2026)
- [Low-light Image Enhancement via Multi-scale Attention combined with Fourier Transform](https://mlsanity.com/paper/2607.24002/) (2026)

## Abstract (arXiv)

Current Low-light Image Enhancement (LLIE) techniques predominantly rely on either direct Low-Light (LL) to Normal-Light (NL) mappings or guidance from semantic features or illumination maps. Nonetheless, the intrinsic ill-posedness of LLIE and the difficulty in retrieving robust semantics from heavily corrupted images hinder their effectiveness in extremely low-light environments. To tackle this challenge, we present SG-LLIE, a new multi-scale CNN-Transformer hybrid framework guided by structure priors. Different from employing pre-trained models for the extraction of semantics or illumination maps, we choose to extract robust structure priors based on illumination-invariant edge detectors. Moreover, we develop a CNN-Transformer Hybrid Structure-Guided Feature Extractor (HSGFE) module at each scale with in the UNet encoder-decoder architecture. Besides the CNN blocks which excels in multi-scale feature extraction and fusion, we introduce a Structure-Guided Transformer Block (SGTB) in each HSGFE that incorporates structural priors to modulate the enhancement process. Extensive experiments show that our method achieves state-of-the-art performance on several LLIE benchmarks in both quantitative metrics and visual quality. Our solution ranks second in the NTIRE 2025 Low-Light Enhancement Challenge. Code is released at https://github.com/minyan8/imagine.