Toward Fast, Flexible, and Robust Low-Light Image Enhancement

By Long Ma, Tengyu Ma, Risheng Liu, Xin Fan, Zhongxuan Luo. Computer Vision and Pattern Recognition, 2022

313 citations recorded by the source corpus.

Existing low-light image enhancement techniques are mostly not only difficult to deal with both visual quality and computational efficiency but also commonly invalid in unknown complex scenarios. In this paper, we develop a new Self-Calibrated Illumination (SCI) learning framework for fast, flexible, and robust brightening images in real-world low-light scenarios. To be specific, we establish a cascaded illumination learning process with weight sharing to handle this task. Considering the computational burden of the cascaded pattern, we construct the self-calibrated module which realizes the convergence between results of each stage, producing the gains that only use the single basic block for inference (yet has not been exploited in previous works), which drastically diminishes computation cost. We then define the unsupervised training loss to elevate the model capability that can adapt general scenes. Further, we make comprehensive explorations to excavate SCI's inherent properties (lacking in existing works) including operation-insensitive adaptability (acquiring stable performance under the settings of different simple operations) and model-irrelevant generality (can be applied to illumination-based existing works to improve performance). Finally, plenty of experiments and ablation studies fully indicate our superiority in both quality and efficiency. Applications on low-light face detection and nighttime semantic segmentation fully reveal the latent practical values for SCI. The source code is available at https://github.com/vis-opt-group/SCI.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cbaeb612e208eac2723f6d7a3e7f66350c10c801

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

Citations in the corpus

Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation (2023, background): “Recently, few studies[13, 14, 15, 16, 17] have attempted to design multi-task learning-based loss functions by cascading the fusion network and high-level tasks.”
Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement (2023, methodology): “Our Retinexformer achieves the highest result on average, 66.1 AP, which is 0.5 AP higher than the recent best self-supervised method SCI [37] and 0.8 AP higher than the recent best fully-supervised method SNR-Net [57].”
Low-Light Image Enhancement with Wavelet-Based Diffusion Models (2023, background): “1, both unsupervised SCI [Ma et al. 2022] and supervised SNRNet [Xu et al. 2022] appear incorrectly overexposed in the background region.”