A Lightweight Real-Time Low-Light Enhancement Network for Embedded Automotive Vision Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909940416774144 |
|---|---|
| author | Chen, Yuhan Shi, Yicui Li, Guofa Bai, Guangrui Shao, Jinyuan Huang, Xiangfei Chu, Wenbo Li, Keqiang |
| author_facet | Chen, Yuhan Shi, Yicui Li, Guofa Bai, Guangrui Shao, Jinyuan Huang, Xiangfei Chu, Wenbo Li, Keqiang |
| contents | In low-light environments like nighttime driving, image degradation severely challenges in-vehicle camera safety. Since existing enhancement algorithms are often too computationally intensive for vehicular applications, we propose UltraFast-LieNET, a lightweight multi-scale shifted convolutional network for real-time low-light image enhancement. We introduce a Dynamic Shifted Convolution (DSConv) kernel with only 12 learnable parameters for efficient feature extraction. By integrating DSConv with varying shift distances, a Multi-scale Shifted Residual Block (MSRB) is constructed to significantly expand the receptive field. To mitigate lightweight network instability, a residual structure and a novel multi-level gradient-aware loss function are incorporated. UltraFast-LieNET allows flexible parameter configuration, with a minimum size of only 36 parameters. Results on the LOLI-Street dataset show a PSNR of 26.51 dB, outperforming state-of-the-art methods by 4.6 dB while utilizing only 180 parameters. Experiments across four benchmark datasets validate its superior balance of real-time performance and enhancement quality under limited resources. Code is available at https://githubhttps://github.com/YuhanChen2024/UltraFast-LiNET |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_02965 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Lightweight Real-Time Low-Light Enhancement Network for Embedded Automotive Vision Systems Chen, Yuhan Shi, Yicui Li, Guofa Bai, Guangrui Shao, Jinyuan Huang, Xiangfei Chu, Wenbo Li, Keqiang Computer Vision and Pattern Recognition In low-light environments like nighttime driving, image degradation severely challenges in-vehicle camera safety. Since existing enhancement algorithms are often too computationally intensive for vehicular applications, we propose UltraFast-LieNET, a lightweight multi-scale shifted convolutional network for real-time low-light image enhancement. We introduce a Dynamic Shifted Convolution (DSConv) kernel with only 12 learnable parameters for efficient feature extraction. By integrating DSConv with varying shift distances, a Multi-scale Shifted Residual Block (MSRB) is constructed to significantly expand the receptive field. To mitigate lightweight network instability, a residual structure and a novel multi-level gradient-aware loss function are incorporated. UltraFast-LieNET allows flexible parameter configuration, with a minimum size of only 36 parameters. Results on the LOLI-Street dataset show a PSNR of 26.51 dB, outperforming state-of-the-art methods by 4.6 dB while utilizing only 180 parameters. Experiments across four benchmark datasets validate its superior balance of real-time performance and enhancement quality under limited resources. Code is available at https://githubhttps://github.com/YuhanChen2024/UltraFast-LiNET |
| title | A Lightweight Real-Time Low-Light Enhancement Network for Embedded Automotive Vision Systems |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.02965 |