CEDFlow: Latent Contour Enhancement for Dark Optical Flow Estimation
DOI:
https://doi.org/10.1609/aaai.v38i7.28627Keywords:
CV: Scene Analysis & Understanding, CV: Computational Photography, Image & Video Synthesis, CV: Learning & Optimization for CVAbstract
Accurately computing optical flow in low-contrast and noisy dark images is challenging, especially when contour information is degraded or difficult to extract. This paper proposes CEDFlow, a latent space contour enhancement for estimating optical flow in dark environments. By leveraging spatial frequency feature decomposition, CEDFlow effectively encodes local and global motion features. Importantly, we introduce the 2nd-order Gaussian difference operation to select salient contour features in the latent space precisely. It is specifically designed for large-scale contour components essential in dark optical flow estimation. Experimental results on the FCDN and VBOF datasets demonstrate that CEDFlow outperforms state-of-the-art methods in terms of the EPE index and produces more accurate and robust flow estimation. Our code is available at: https://github.com/xautstuzfy.Downloads
Published
2024-03-24
How to Cite
Zuo, F., Xiao, Z., Jin, H., & Su, H. (2024). CEDFlow: Latent Contour Enhancement for Dark Optical Flow Estimation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(7), 7909-7916. https://doi.org/10.1609/aaai.v38i7.28627
Issue
Section
AAAI Technical Track on Computer Vision VI