Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.09650 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918303921864704 |
|---|---|
| author | Adhikarla, Eashan Zhang, Kai Chen, Gong Nicholson, John Davison, Brian D. |
| author_facet | Adhikarla, Eashan Zhang, Kai Chen, Gong Nicholson, John Davison, Brian D. |
| contents | Low-light image enhancement remains a persistent challenge in computer vision, where state-of-the-art models are often hampered by hardware constraints and computational inefficiency, particularly at high resolutions. While foundational architectures like transformers and diffusion models have advanced the field, their computational complexity limits their deployment on edge devices. We introduce ExpoMamba, a novel architecture that integrates a frequency-aware state-space model within a modified U-Net. ExpoMamba is designed to address mixed-exposure challenges by decoupling the modeling of amplitude (intensity) and phase (structure) in the frequency domain. This allows for targeted enhancement, making it highly effective for real-time applications, including downstream tasks like object detection and segmentation. Our experiments on six benchmark datasets show that ExpoMamba is up to 2-3x faster than competing models and achieves a 6.8\% PSNR improvement, establishing a new state-of-the-art in efficient, high-quality low-light enhancement. Source code: https://www.github.com/eashanadhikarla/ExpoMamba. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09650 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision Adhikarla, Eashan Zhang, Kai Chen, Gong Nicholson, John Davison, Brian D. Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Image and Video Processing Low-light image enhancement remains a persistent challenge in computer vision, where state-of-the-art models are often hampered by hardware constraints and computational inefficiency, particularly at high resolutions. While foundational architectures like transformers and diffusion models have advanced the field, their computational complexity limits their deployment on edge devices. We introduce ExpoMamba, a novel architecture that integrates a frequency-aware state-space model within a modified U-Net. ExpoMamba is designed to address mixed-exposure challenges by decoupling the modeling of amplitude (intensity) and phase (structure) in the frequency domain. This allows for targeted enhancement, making it highly effective for real-time applications, including downstream tasks like object detection and segmentation. Our experiments on six benchmark datasets show that ExpoMamba is up to 2-3x faster than competing models and achieves a 6.8\% PSNR improvement, establishing a new state-of-the-art in efficient, high-quality low-light enhancement. Source code: https://www.github.com/eashanadhikarla/ExpoMamba. |
| title | From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Multimedia Image and Video Processing |
| url | https://arxiv.org/abs/2408.09650 |