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the assumption is no longer valid for the differently exposed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.