CEDFlow: Latent Contour Enhancement for Dark Optical Flow Estimation
Fengyuan Zuo, Zhaolin Xiao, Haiyan Jin, Haonan Su
Abstract
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.
BibTeX
@article{Zuo_Xiao_Jin_Su_2024, title={CEDFlow: Latent Contour Enhancement for Dark Optical Flow Estimation}, volume={38}, url={https://ojs.aaai.org/index.php/AAAI/article/view/28627}, DOI={10.1609/aaai.v38i7.28627}, abstractNote={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.}, number={7}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Zuo, Fengyuan and Xiao, Zhaolin and Jin, Haiyan and Su, Haonan}, year={2024}, month={Mar.}, pages={7909-7916} }