PatchBatch: A Batch Augmented Loss for Optical Flow
David Gadot,Lior Wolf +1 more
- 01 Jun 2016
- pp 4236-4245
TL;DR: In this paper, a Siamese CNN is used to independently and in parallel compute the descriptors of both images, which are then compared efficiently using the L2 norm and do not require network processing of patch pairs.
read more
Abstract: We propose a new pipeline for optical flow computation, based on Deep Learning techniques. We suggest using a Siamese CNN to independently, and in parallel, compute the descriptors of both images. The learned descriptors are then compared efficiently using the L2 norm and do not require network processing of patch pairs. The success of the method is based on an innovative loss function that computes higher moments of the loss distributions for each training batch. Combined with an Approximate Nearest Neighbor patch matching method and a flow interpolation technique, state of the art performance is obtained on the most challenging and competitive optical flow benchmarks.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Eddy Ilg,Nikolaus Mayer,Tonmoy Saikia,Margret Keuper,Alexey Dosovitskiy,Thomas Brox +5 more
- 21 Jul 2017
TL;DR: The concept of end-to-end learning of optical flow is advanced and it work really well, and faster variants that allow optical flow computation at up to 140fps with accuracy matching the original FlowNet are presented.
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
Deqing Sun,Xiaodong Yang,Ming-Yu Liu,Jan Kautz +3 more
- 01 Jun 2018
TL;DR: PWC-Net as discussed by the authors uses the current optical flow estimate to warp the CNN features of the second image, which is processed by a CNN to estimate the optical flow, and achieves state-of-the-art performance on the MPI Sintel final pass and KITTI 2015 benchmarks.
•Posted Content
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
TL;DR: FlowNet 2.0 as discussed by the authors proposes an end-to-end learning framework for optical flow estimation, which is only marginally slower than the original FlowNet but decreases the estimation error by more than 50%.
1.9K
VoxelMorph: A Learning Framework for Deformable Medical Image Registration
TL;DR: VoxelMorph promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications and demonstrates that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster.
Video Frame Interpolation via Adaptive Separable Convolution
Simon Niklaus,Long Mai,Feng Liu +2 more
- 01 Oct 2017
TL;DR: In this article, a deep fully convolutional neural network is proposed to estimate pairs of 1D kernels for all pixels simultaneously, which allows for the incorporation of perceptual loss to train the network to produce visually pleasing frames.
References
•Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
- 04 Sep 2014
TL;DR: This work investigates the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting using an architecture with very small convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers.
102.6K
•Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
- 06 Jul 2015
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.
Are we ready for autonomous driving? The KITTI vision benchmark suite
Andreas Geiger,Philip Lenz,Raquel Urtasun +2 more
- 16 Jun 2012
TL;DR: The autonomous driving platform is used to develop novel challenging benchmarks for the tasks of stereo, optical flow, visual odometry/SLAM and 3D object detection, revealing that methods ranking high on established datasets such as Middlebury perform below average when being moved outside the laboratory to the real world.
Determining optical flow
TL;DR: In this paper, a method for finding the optical flow pattern is presented which assumes that the apparent velocity of the brightness pattern varies smoothly almost everywhere in the image, and an iterative implementation is shown which successfully computes the Optical Flow for a number of synthetic image sequences.
12.4K
•Book
Determining optical flow
Berthold K. P. Horn,Brian G. Schunck +1 more
- 03 Jan 1992
TL;DR: An iterative implementation is shown which successfully computes the optical flow for a number of synthetic image sequences and is robust in that it can handle image sequences that are quantified rather coarsely in space and time.