Supplementary Material for LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation

We use the tool provided in Sintel evaluation kit [1] to visualize flow fields in the main paper [2] and supplementary material. Fig. 1 illustrates the color code used in the visualization. Flow direction is encoded with color while magnitude is encoded with color intensity. Particularly, white color at the center corresponds to no visual motion. For the ease of visual evaluation, flow fields among the compared methods are normalized by the maximum flow magnitude of the ground truth (when evaluation is performed on training set) or LiteFlowNet3 [2] (when evaluation is performed on testing set) prior to the computing of flow color.

[1]  Trevor Darrell,et al.  Hierarchical Discrete Distribution Decomposition for Match Density Estimation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Tak-Wai Hui,et al.  LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation , 2020, ECCV.

[3]  Thomas Brox,et al.  FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[4]  Michael J. Black,et al.  Optical Flow Estimation Using a Spatial Pyramid Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Stefan Roth,et al.  Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Michael J. Black,et al.  A Naturalistic Open Source Movie for Optical Flow Evaluation , 2012, ECCV.

[7]  Xiaoou Tang,et al.  A Lightweight Optical Flow CNN —Revisiting Data Fidelity and Regularization , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Michael R. Lyu,et al.  SelFlow: Self-Supervised Learning of Optical Flow , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Jan Kautz,et al.  Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[10]  Jan Kautz,et al.  PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[11]  Xiaoou Tang,et al.  LiteFlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.