SNR-Aware Low-light Image Enhancement
By Xiaogang Xu, Ruixing Wang, Chiao Fu, Jiaya Jia. Computer Vision and Pattern Recognition, 2022
671 citations recorded by the source corpus.
This paper presents a new solution for low-light image enhancement by collectively exploiting Signal-to-Noise-Ratio-aware transformers and convolutional models to dynamically enhance pixels with spatial-varying operations. They are long-range operations for image regions of extremely low Signal-to-Noise-Ratio (SNR) and short-range operations for other regions. We propose to take an SNR prior to guide the feature fusion and formulate the SNR-aware transformer with a new self-attention model to avoid tokens from noisy image regions of very low SNR. Extensive experiments show that our framework consistently achieves better performance than SOTA approaches on seven representative benchmarks with the same structure. Also, we conducted a large-scale user study with 100 participants to verify the superior perceptual quality of our results. The code is available at https://github.com/dvlab-research/SNR-Aware-Low-Light-Enhance.
Subfields: Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/4ac44c6f7cbc49293733540ab4b27a8ce31f3149
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
In Media Technology
Citations in the corpus
- Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (2023, methodology): “Some CNN-Transformer hybrid works like SNR-Net [57] only employ a global Transformer layer at the lowest resolution of a U-shaped CNN due to the enormous computational complexity of global multi-head self-attention (MSA).”