IVCVDec 4, 2021

Efficient joint noise removal and multi exposure fusion

arXiv:2112.03701v1
Originality Incremental advance
AI Analysis

This work addresses noise removal in multi-exposure fusion for image processing applications, presenting an incremental improvement by integrating denoising into the fusion chain.

The paper tackles the problem of combining multiple exposure images while removing noise, proposing a joint fusion and denoising method that uses DCT processing, spatio-temporal patch selection, and collaborative 3D thresholding, resulting in an efficient procedure that avoids recovering each denoised exposure image.

Multi-exposure fusion (MEF) is a technique for combining different images of the same scene acquired with different exposure settings into a single image. All the proposed MEF algorithms combine the set of images, somehow choosing from each one the part with better exposure. We propose a novel multi-exposure image fusion chain taking into account noise removal. The novel method takes advantage of DCT processing and the multi-image nature of the MEF problem. We propose a joint fusion and denoising strategy taking advantage of spatio-temporal patch selection and collaborative 3D thresholding. The overall strategy permits to denoise and fuse the set of images without the need of recovering each denoised exposure image, leading to a very efficient procedure.

Foundations

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

Your Notes