Affordable Access

deepdyve-link
Publisher Website

Deep Guided Learning for Fast Multi-Exposure Image Fusion.

Authors
  • Ma, Kede
  • Duanmu, Zhengfang
  • Zhu, Hanwei
  • Fang, Yuming
  • Wang, Zhou
Type
Published Article
Journal
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers
Publication Date
Nov 19, 2019
Identifiers
DOI: 10.1109/TIP.2019.2952716
PMID: 31751238
Source
Medline
Language
English
License
Unknown

Abstract

We propose a fast multi-exposure image fusion (MEF) method, namely MEF-Net, for static image sequences of arbitrary spatial resolution and exposure number. We first feed a low-resolution version of the input sequence to a fully convolutional network for weight map prediction. We then jointly upsample the weight maps using a guided filter. The final image is computed by a weighted fusion. Unlike conventional MEF methods, MEF-Net is trained end-to-end by optimizing the perceptually calibrated MEF structural similarity (MEF-SSIM) index over a database of training sequences at full resolution. Across an independent set of test sequences, we find that the optimized MEF-Net achieves consistent improvement in visual quality for most sequences, and runs 10 to 1000 times faster than state-of-the-art methods. The code is made publicly available at.

Report this publication

Statistics

Seen <100 times