Unsupervised Optical Flow Estimation for Differently Exposed Images in LDR Domain

Page view(s)
61
Checked on Feb 16, 2025
Unsupervised Optical Flow Estimation for Differently Exposed Images in LDR Domain
Title:
Unsupervised Optical Flow Estimation for Differently Exposed Images in LDR Domain
Journal Title:
IEEE Transactions on Circuits and Systems for Video Technology
Publication URL:
Publication Date:
03 March 2023
Citation:
Liu, Z., Li, Z., Chen, W., Wu, X., & Liu, Z. (2023). Unsupervised Optical Flow Estimation for Differently Exposed Images in LDR Domain. IEEE Transactions on Circuits and Systems for Video Technology, 33(10), 5332–5344. https://doi.org/10.1109/tcsvt.2023.3252007
Abstract:
Differently exposed low dynamic range (LDR) images are often captured sequentially using a smart phone or a digital camera with movements. Optical flow thus plays an important role in ghost removal for high dynamic range (HDR) imaging. The optical flow estimation is based on the theory of photometric consistency, which assumes that the corresponding pixels between two images have the same intensity. However, the assumption is no longer valid for the differently exposed LDR images since a pixel’s intensity changes significantly inter images. To address the problem, an unsupervised optical flow estimation framework, is presented in this study. Intensity mapping functions (IMFs) are first adopted to alleviate the intensity changes between the LDR images. Then a novel IMF-based unsupervised learning objective is proposed to circumvent the need for ground truth optical flows when training the deep network. Experimental results and ablation studies on publicly available datasets show that our framework outperforms the state-of-the-art unsupervised optical flow methods, demonstrating the effectiveness of the IMF and the learning objective. Our code is available at https://github.com/liuziyang123/LDRFlow.
License type:
Publisher Copyright
Funding Info:
This work is supported by National Natural Science Foundation of China under Grant No. 61620106012.
Description:
© 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
ISSN:
1558-2205
1051-8215
Files uploaded:

File Size Format Action
ldrflow-0117.pdf 10.82 MB PDF Request a copy