Continual Occlusions and Optical Flow Estimation

Two optical flow estimation problems are addressed: i) occlusion estimation and handling, and ii) estimation from image sequences longer than two frames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use of flow corrupted by occlusions for their estimation. We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25\% on both KITTI and Sintel. As a second contribution, a novel method for incorporating information from past frames into flow estimation is introduced. The previous frame flow serves as an input to occlusion estimation and as a prior in occluded regions, i.e. those without visual correspondences. By continually using the previous frame flow, ContinualFlow performance improves further by 18\% on KITTI and 7\% on Sintel, achieving top performance on KITTI and Sintel.

[1]  Andreas Geiger,et al.  Object scene flow for autonomous vehicles , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Horst Bischof,et al.  Joint motion estimation and segmentation of complex scenes with label costs and occlusion modeling , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[5]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

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

[7]  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.

[8]  Daniel Rueckert,et al.  Dense Multi-frame Optic Flow for Non-rigid Objects Using Subspace Constraints , 2010, ACCV.

[9]  Berthold K. P. Horn,et al.  Determining Optical Flow , 1981, Other Conferences.

[10]  Andrés Bruhn,et al.  ProFlow: Learning to Predict Optical Flow , 2018, BMVC.

[11]  Henning Zimmer,et al.  Modeling temporal coherence for optical flow , 2011, 2011 International Conference on Computer Vision.

[12]  Andreas Geiger,et al.  Deep Discrete Flow , 2016, ACCV.

[13]  Qiao Wang,et al.  VirtualWorlds as Proxy for Multi-object Tracking Analysis , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[15]  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.

[16]  Didier Stricker,et al.  FlowFields++: Accurate Optical Flow Correspondences Meet Robust Interpolation , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[17]  Didier Stricker,et al.  Flow Fields: Dense Correspondence Fields for Highly Accurate Large Displacement Optical Flow Estimation , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Vladlen Koltun,et al.  Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[19]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Stefan Roth,et al.  UnFlow: Unsupervised Learning of Optical Flow with a Bidirectional Census Loss , 2017, AAAI.

[21]  Bernd Jähne,et al.  The HCI Benchmark Suite: Stereo and Flow Ground Truth with Uncertainties for Urban Autonomous Driving , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[22]  David W. Murray,et al.  Scene Segmentation from Visual Motion Using Global Optimization , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Michal Irani,et al.  Multi-Frame Correspondence Estimation Using Subspace Constraints , 2002, International Journal of Computer Vision.

[24]  Deqing Sun,et al.  Local Layering for Joint Motion Estimation and Occlusion Detection , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Thomas Brox,et al.  FlowNet: Learning Optical Flow with Convolutional Networks , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[26]  Thomas Brox,et al.  A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Michael J. Black,et al.  Robust dynamic motion estimation over time , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[28]  Qiong Yan,et al.  Cascade Residual Learning: A Two-Stage Convolutional Neural Network for Stereo Matching , 2017, 2017 IEEE International Conference on Computer Vision Workshops (ICCVW).

[29]  Lourdes Agapito,et al.  A Variational Approach to Video Registration with Subspace Constraints , 2013, International Journal of Computer Vision.

[30]  Stefan Roth,et al.  MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[31]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[32]  Daniel Cremers,et al.  What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation? , 2018, International Journal of Computer Vision.

[33]  Didier Stricker,et al.  Supplementary material of : CNN-based Patch Matching for Optical Flow with Thresholded Hinge Embedding Loss , 2017 .

[34]  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).

[35]  Kurt Keutzer,et al.  Dense Point Trajectories by GPU-Accelerated Large Displacement Optical Flow , 2010, ECCV.

[36]  Hui Cheng,et al.  Bilateral Filtering-Based Optical Flow Estimation with Occlusion Detection , 2006, ECCV.

[37]  Javier Sánchez Pérez,et al.  TV-L1 Optical Flow Estimation , 2013, Image Process. Line.

[38]  Cordelia Schmid,et al.  DeepFlow: Large Displacement Optical Flow with Deep Matching , 2013, 2013 IEEE International Conference on Computer Vision.

[39]  Richard Szeliski,et al.  A Database and Evaluation Methodology for Optical Flow , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[40]  Luc Van Gool,et al.  One-Shot Video Object Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Michael J. Black,et al.  Optical Flow in Mostly Rigid Scenes , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).