CVDec 18, 2014

Image Dynamic Range Enhancement in the Context of Logarithmic Models

arXiv:1412.5764v15 citations
Originality Synthesis-oriented
AI Analysis

This work provides a theoretical and practical solution for image enhancement in computer vision, though it appears incremental as it builds on existing logarithmic models.

The authors addressed the problem of identifying and obtaining a privileged image representation under variable illumination or aperture conditions using logarithmic models, resulting in two transforms for optimal dynamic range and mean dynamic range enhancement with experimental validation.

Images of a scene observed under a variable illumination or with a variable optical aperture are not identical. Does a privileged representant exist? In which mathematical context? How to obtain it? The authors answer to such questions in the context of logarithmic models for images. After a short presentation of the model, the paper presents two image transforms: one performs an optimal enhancement of the dynamic range, and the other does the same for the mean dynamic range. Experimental results are shown.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes