SKFlow: Learning Optical Flow with Super Kernels

Optical flow estimation is a classical yet challenging task in computer vision. One of the essential factors in accurately predicting optical flow is to alleviate occlusions between frames. However, it is still a thorny problem for current top-performing optical flow estimation methods due to insufficient local evidence to model occluded areas. In this paper, we propose the Super Kernel Flow Network (SKFlow), a CNN architecture to ameliorate the impacts of occlusions on optical flow estimation. SKFlow benefits from the super kernels which bring enlarged receptive fields to complement the absent matching information and recover the occluded motions. We present efficient super kernel designs by utilizing conical connections and hybrid depth-wise convolutions. Extensive experiments demonstrate the effectiveness of SKFlow on multiple benchmarks, especially in the occluded areas. Without pre-trained backbones on ImageNet and with a modest increase in computation, SKFlow achieves compelling performance and ranks $\textbf{1st}$ among currently published methods on the Sintel benchmark. On the challenging Sintel clean and final passes (test), SKFlow surpasses the best-published result in the unmatched areas ($7. 96$ and $12. 50$) by $9. 09\%$ and $7. 92\%$. The code is available at https: //github. com/littlespray/SKFlow.

Authors

• Shangkun Sun Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, School of Electronic and Computer Engineering, Shenzhen Graduate School, Peking University, Shenzhen 518055, China, Peng Cheng Laboratory
• Yuanqi Chen
• Yu Zhu Institute of Automation, Chinese Academy of Science; School of Artifcial Intelligence, University of Chinese Academy of Sciences
• Guodong Guo Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China
• Ge Li Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology, Shenzhen Graduate School, Peking University

Keywords

No keywords are indexed for this paper.