Scalable Full Flow with Learned Binary Descriptors

We propose a method for large displacement optical flow in which local matching costs are learned by a convolutional neural network (CNN) and a smoothness prior is imposed by a conditional random field (CRF). We tackle the computation- and memory-intensive operations on the 4D cost volume by a min-projection which reduces memory complexity from quadratic to linear and binary descriptors for efficient matching. This enables evaluation of the cost on the fly and allows to perform learning and CRF inference on high resolution images without ever storing the 4D cost volume. To address the problem of learning binary descriptors we propose a new hybrid learning scheme. In contrast to current state of the art approaches for learning binary CNNs we can compute the exact non-zero gradient within our model. We compare several methods for training binary descriptors and show results on public available benchmarks.

[1]  Thomas Pock,et al.  End-to-End Training of Hybrid CNN-CRF Models for Stereo , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Raquel Urtasun,et al.  Efficient Deep Learning for Stereo Matching , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Liang Wang,et al.  A Deep Visual Correspondence Embedding Model for Stereo Matching Costs , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[4]  Yann LeCun,et al.  Computing the stereo matching cost with a convolutional neural network , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Martin J. Wainwright,et al.  MAP estimation via agreement on (hyper)trees: Message-passing and linear programming , 2005, ArXiv.

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

[7]  Yoshua Bengio,et al.  Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation , 2013, ArXiv.

[8]  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.

[9]  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).

[10]  Thomas Pock,et al.  Solving Dense Image Matching in Real-Time using Discrete-Continuous Optimization , 2016, ArXiv.

[11]  Jia Xu,et al.  Accurate Optical Flow via Direct Cost Volume Processing , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Yoshua Bengio,et al.  BinaryNet: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1 , 2016, ArXiv.

[13]  Lior Wolf,et al.  PatchBatch: A Batch Augmented Loss for Optical Flow , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Cordelia Schmid,et al.  EpicFlow: Edge-preserving interpolation of correspondences for optical flow , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[16]  Horst Bischof,et al.  Pushing the limits of stereo using variational stereo estimation , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[17]  Thomas Pock,et al.  Non-local Total Generalized Variation for Optical Flow Estimation , 2014, ECCV.

[18]  Vladimir Kolmogorov,et al.  Convergent Tree-Reweighted Message Passing for Energy Minimization , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[19]  Vincent Lepetit,et al.  Boosting Binary Keypoint Descriptors , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[20]  Vincent Lepetit,et al.  BRIEF: Binary Robust Independent Elementary Features , 2010, ECCV.

[21]  Pedro F. Felzenszwalb,et al.  Efficient belief propagation for early vision , 2004, CVPR 2004.

[22]  Václav Hlavác,et al.  Efficient MRF Deformation Model for Non-Rigid Image Matching , 2007, CVPR.

[23]  Martin J. Wainwright,et al.  MAP estimation via agreement on trees: message-passing and linear programming , 2005, IEEE Transactions on Information Theory.

[24]  Igor Carron,et al.  XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks , 2016 .