Chenglong Li
Chenglong Li has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Pai Peng
College of Geographical and Remote Sensing Sciences, Xinjiang University, Urumqi, 830017, China
1 shared publication - Qimeng Yang1 shared publication
- Yixin Sang1 shared publication
Latest Publications
- Open Access
- 2 June 2026
- Published by Elsevier in SSRN Electronic Journal
HDAR-Net: Hierarchical Dual-Attention Network for Zero-Reference Low-Light Image Enhancement
Low-light image enhancement aims to recover well-exposed images from degraded observations. However, existing curve-based zero-reference methods are often limited by shallow architectures with restricted receptive fields and by uniform enhancement strategies that tend to over-enhance already bright regions. To address these issues, we propose HDAR-Net, a Hierarchical Dual-Attention network with Regional protection, which integrates three complementary innovations. First, a hierarchical U-Net encoder-decoder expands the receptive field from 7 × 7 to 127 × 127 pixels, enabling more effective global context modeling. Second, a dual-branch CBAM attention mechanism performs sequential channel and spatial attention, allowing content-adaptive feature selection. Third, a content-aware regional protection module with learnable brightness estimation adaptively regulates enhancement strength, thereby suppressing over-saturation artifacts in bright areas. Extensive experiments on the LOL and SICE benchmarks show that HDAR-Net achieves state-of-the-art performance, reaching PSNR values of 20.16 dB and 18.02 dB, respectively, while remaining computationally efficient with only 2.29 million parameters and an inference speed of 125 FPS, demonstrating its practicality for real-world deployment.
- 2 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessHDAR-Net: Hierarchical Dual-Attention Network for Zero-Reference Low-Light Image Enhancement
Low-light image enhancement aims to recover well-exposed images from degraded observations. However, existing curve-based zero-reference methods are often limited by shallow architectures with restricted receptive fields and by uniform enhancement strategies that tend to over-enhance already bright regions. To address these issues, we propose HDAR-Net, a Hierarchical Dual-Attention network with Regional protection, which integrates three complementary innovations. First, a hierarchical U-Net encoder-decoder expands the receptive field from 7 × 7 to 127 × 127 pixels, enabling more effective global context modeling. Second, a dual-branch CBAM attention mechanism performs sequential channel and spatial attention, allowing content-adaptive feature selection. Third, a content-aware regional protection module with learnable brightness estimation adaptively regulates enhancement strength, thereby suppressing over-saturation artifacts in bright areas. Extensive experiments on the LOL and SICE benchmarks show that HDAR-Net achieves state-of-the-art performance, reaching PSNR values of 20.16 dB and 18.02 dB, respectively, while remaining computationally efficient with only 2.29 million parameters and an inference speed of 125 FPS, demonstrating its practicality for real-world deployment.