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

🤖 Plain-English Summary

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. Applications on low-light face detection and nighttime semantic segmentation fully reveal the latent practical values for SCI.

🔑 Key Findings

• 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.

🔗 Related Resources