DeepSPG: Exploring Deep Semantic Prior Guidance for Low-light Image Enhancement with Multimodal Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913810131976192 |
|---|---|
| author | Lu, Jialang Zhao, Huayu Zhai, Huiyu Yang, Xingxing Han, Shini |
| author_facet | Lu, Jialang Zhao, Huayu Zhai, Huiyu Yang, Xingxing Han, Shini |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_19127 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DeepSPG: Exploring Deep Semantic Prior Guidance for Low-light Image Enhancement with Multimodal Learning Lu, Jialang Zhao, Huayu Zhai, Huiyu Yang, Xingxing Han, Shini Computer Vision and Pattern Recognition Multimedia 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. |
| title | DeepSPG: Exploring Deep Semantic Prior Guidance for Low-light Image Enhancement with Multimodal Learning |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2504.19127 |