Displacement-invariant matching cost learning for accurate optical flow estimation

Jianyuan Wang*, Yiran Zhong*, Yuchao Dai, Kaihao Zhang, Pan Ji, Hongdong Li

*Corresponding author for this work

    Research output: Contribution to journalConference articlepeer-review

    42 Citations (Scopus)


    Learning matching costs has been shown to be critical to the success of the state-of-the-art deep stereo matching methods, in which 3D convolutions are applied on a 4D feature volume to learn a 3D cost volume. However, this mechanism has never been employed for the optical flow task. This is mainly due to the significantly increased search dimension in the case of optical flow computation, i.e., a straightforward extension would require dense 4D convolutions in order to process a 5D feature volume, which is computationally prohibitive. This paper proposes a novel solution that is able to bypass the requirement of building a 5D feature volume while still allowing the network to learn suitable matching costs from data. Our key innovation is to decouple the connection between 2D displacements and learn the matching costs at each 2D displacement hypothesis independently, i.e., displacement-invariant cost learning. Specifically, we apply the same 2D convolution-based matching net independently on each 2D displacement hypothesis to learn a 4D cost volume. Moreover, we propose a displacement-aware projection layer to scale the learned cost volume, which reconsiders the correlation between different displacement candidates and mitigates the multi-modal problem in the learned cost volume. The cost volume is then projected to optical flow estimation through a 2D soft-argmin layer. Extensive experiments show that our approach achieves state-of-the-art accuracy on various datasets, and outperforms all published optical flow methods on the Sintel benchmark. The code is available at https://github.com/jytime/DICL-Flow.

    Original languageEnglish
    JournalAdvances in Neural Information Processing Systems
    Publication statusPublished - 2020
    Event34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
    Duration: 6 Dec 202012 Dec 2020


    Dive into the research topics of 'Displacement-invariant matching cost learning for accurate optical flow estimation'. Together they form a unique fingerprint.

    Cite this