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 https://github.com/makedede/MEFNet. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/TIP.2019.2952716 | IEEE TRANSACTIONS ON IMAGE PROCESSING |
Keywords | DocType | Volume |
Multi-exposure image fusion, convolutional neural networks, guided filtering, computational photography | Journal | 29 |
Issue | ISSN | Citations |
1 | 1057-7149 | 2 |
PageRank | References | Authors |
0.37 | 21 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Kede Ma | 1 | 773 | 27.93 |
Zhengfang Duanmu | 2 | 171 | 8.24 |
Hanwei Zhu | 3 | 6 | 2.13 |
Yuming Fang | 4 | 1247 | 75.50 |
Z Wang | 5 | 13331 | 630.91 |