AutoLumNet framework offers state-of-the-art single-shot image exposure correction

Researchers have introduced AutoLumNet, a novel framework designed for single-shot exposure correction in images. This system decomposes the correction process into a global monotone tone curve and a local residual, ensuring that the global component adheres to formal guarantees. The tone curve is constructed to preserve luminance ordering and is optimized using a sorted-sample Wasserstein-2 objective. The framework also addresses local effects like shading and color shifts with a bounded residual decoder. Experiments on five benchmarks demonstrate AutoLumNet's state-of-the-art performance in terms of PSNR and SSIM, with fast processing speeds and effective generalization to low-light conditions without retraining. AI

IMPACT This research advances image processing techniques by offering a more robust and efficient method for exposure correction, potentially improving visual quality in various applications.

RANK_REASON The cluster contains a research paper detailing a new method for image processing. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CV →

• arXiv
• AutoLumNet
• LOL-v1
• LOL-v2-real
• MSEC
• peak signal-to-noise ratio
• SICE
• Structural Similarity Index Measure

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →