Redefining Well Exposedness for Locally Adaptive Multi-Exposure Fusion

Abstract

Multi-exposure fusion combines bracketed exposure captures into a single image with enhanced details from a large dynamic range. It is an effective and resource-efficient way to obtain a high dynamic range image, which has broad applications. Despite significant advancements in the field, existing methods often struggle with artifacts and fall short of preserving the local details while being compute-intensive. Previous similar training-free approaches compute weight maps for fusing the exposure stack, which requires finding how well-exposed each image is. In this paper, we work on the fundamentals to define a novel, well-exposedness function along with a tile-based processing approach. Our approach provides improved image quality with better detail recovery. It outperforms the current state-of-the-art training-free methods both qualitatively and quantitatively while being better suited for onboard processing.