JOURNAL ARTICLE

Fast Multi-Scale Structural Patch Decomposition for Multi-Exposure Image Fusion

Hui LiKede MaHongwei YongLei Zhang

Year: 2020 Journal:   IEEE Transactions on Image Processing Vol: 29 Pages: 5805-5816   Publisher: Institute of Electrical and Electronics Engineers

Abstract

Exposure bracketing is crucial to high dynamic range imaging, but it is prone to halos for static scenes and ghosting artifacts for dynamic scenes. The recently proposed structural patch decomposition for multi-exposure fusion (SPD-MEF) has achieved reliable performance in deghosting, but suffers from visible halo artifacts and is computationally expensive. In addition, its relationship to other MEF methods is unclear. We show that without explicitly performing structural patch decomposition, we arrive at an unnormalized version of SPD-MEF, which enjoys an order of 30× speed-up, and is closely related to pixel-level MEF methods as well as the standard two-layer decomposition method for MEF. Moreover, we develop a fast multi-scale SPD-MEF method, which can effectively reduce halo artifacts. Experimental results demonstrate the effectiveness of the proposed MEF method in terms of speed and quality.

Keywords:
Ghosting Computer science Pixel Image fusion Artificial intelligence High-dynamic-range imaging Halo High dynamic range Computer vision Dynamic range Fusion Scale (ratio) Image (mathematics) Algorithm Physics

Metrics

174
Cited By
19.95
FWCI (Field Weighted Citation Impact)
54
Refs
0.99
Citation Normalized Percentile
Is in top 1%
Is in top 10%

Citation History

Topics

Advanced Image Fusion Techniques
Physical Sciences →  Engineering →  Media Technology
Image Enhancement Techniques
Physical Sciences →  Computer Science →  Computer Vision and Pattern Recognition
Photoacoustic and Ultrasonic Imaging
Physical Sciences →  Engineering →  Biomedical Engineering
© 2026 ScienceGate Book Chapters — All rights reserved.