# DeepSPG: Exploring Deep Semantic Prior Guidance for Low-light Image Enhancement with Multimodal Learning

arXiv: https://arxiv.org/abs/2504.19127 · HTML: https://mlsanity.com/paper/2504.19127/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 12 references that are in the map.
- First posted on arXiv 27 Apr 2025.

## Builds on (most cited first, 5 of 5)

- [LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancement](https://mlsanity.com/paper/1511.03995/) (2015)
- [Ultra-High-Definition Low-Light Image Enhancement: A Benchmark and Transformer-Based Method](https://mlsanity.com/paper/2212.11548/) (2022)
- [Unpaired Image Enhancement Featuring Reinforcement-Learning-Controlled Image Editing Software](https://mlsanity.com/paper/1912.07833/) (2019)
- [Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues](https://mlsanity.com/paper/2312.11119/) (2023)
- [Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR Image Spectrum Translation](https://mlsanity.com/paper/2308.03348/) (2023)

## Built on by (most cited first, 1 of 1)

- [HVI-CIDNet+: Beyond Extreme Darkness for Low-Light Image Enhancement](https://mlsanity.com/paper/2507.06814/) (2025)

## Abstract (arXiv)

There has long been a belief that high-level semantics learning can benefit various downstream computer vision tasks. However, in the low-light image enhancement (LLIE) community, existing methods learn a brutal mapping between low-light and normal-light domains without considering the semantic information of different regions, especially in those extremely dark regions that suffer from severe information loss. To address this issue, we propose a new deep semantic prior-guided framework (DeepSPG) based on Retinex image decomposition for LLIE to explore informative semantic knowledge via a pre-trained semantic segmentation model and multimodal learning. Notably, we incorporate both image-level semantic prior and text-level semantic prior and thus formulate a multimodal learning framework with combinatorial deep semantic prior guidance for LLIE. Specifically, we incorporate semantic knowledge to guide the enhancement process via three designs: an image-level semantic prior guidance by leveraging hierarchical semantic features from a pre-trained semantic segmentation model; a text-level semantic prior guidance by integrating natural language semantic constraints via a pre-trained vision-language model; a multi-scale semantic-aware structure that facilitates effective semantic feature incorporation. Eventually, our proposed DeepSPG demonstrates superior performance compared to state-of-the-art methods across five benchmark datasets. The implementation details and code are publicly available at https://github.com/Wenyuzhy/DeepSPG.