Unsupervised convolutional neural networks for motion estimation

Ahmadi, Arash; Patras, Ioannis

doi:10.48550/arxiv.1601.06087

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The performance is below the state of the art and the method is not tested on the standard benchmarks. There have also been several attempts at estimating optical flow using unsupervised learning [3,45]. However these methods have lower accuracy on standard benchmarks.…”

Section: Related Workmentioning

confidence: 99%

Optical Flow Estimation Using a Spatial Pyramid Network

Ranjan

Black

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

1,149

783

View full text Add to dashboard Cite

We learn to compute optical flow by combining a classical spatial-pyramid formulation with deep learning. This estimates large motions in a coarse-to-fine approach by warping one image of a pair at each pyramid level by the current flow estimate and computing an update to the flow. Instead of the standard minimization of an objective function at each pyramid level, we train one deep network per level to compute the flow update. Unlike the recent FlowNet approach, the networks do not need to deal with large motions; these are dealt with by the pyramid. This has several advantages. First, our Spatial Pyramid Network (SPyNet) is much simpler and 96% smaller than FlowNet in terms of model parameters. This makes it more efficient and appropriate for embedded applications. Second, since the flow at each pyramid level is small (< 1 pixel), a convolutional approach applied to pairs of warped images is appropriate. Third, unlike FlowNet, the learned convolution filters appear similar to classical spatio-temporal filters, giving insight into the method and how to improve it. Our results are more accurate than FlowNet on most standard benchmarks, suggesting a new direction of combining classical flow methods with deep learning.

show abstract

Section: Related Workmentioning

confidence: 99%

Optical Flow Estimation Using a Spatial Pyramid Network

Ranjan

Black

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

1,149

783

View full text Add to dashboard Cite

show abstract

“…Instead, Ahmadi and Patras [1] and Yu et al [32] formulated the task as an unsupervised learning problem. To this end, they used a cost function based on the classical color constancy assumption, as it is used in variational techniques.…”

Section: Related Workmentioning

confidence: 99%

Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild

Sedaghat,

Zolfaghari,

Brox

2016

Preprint

View full text Add to dashboard Cite

CNN-based optical flow estimation has attracted attention recently, mainly due to its impressively high frame rates. These networks perform well on synthetic datasets, but they are still far behind the classical methods in realworld videos. This is because there is no ground truth optical flow for training these networks on real data. In this paper, we boost CNN-based optical flow estimation in real scenes with the help of the freely available self-supervised task of next-frame prediction. To this end, we train the network in a hybrid way, providing it with a mixture of synthetic and real videos. With the help of a sample-variant multi-tasking architecture, the network is trained on different tasks depending on the availability of ground-truth. We also experiment with the prediction of "next-flow" instead of estimation of the current flow, which is intuitively closer to the task of next-frame prediction and yields favorable results. We demonstrate the improvement in optical flow estimation on the real-world KITTI benchmark. Additionally, we test the optical flow indirectly in an action classification scenario. As a side product of this work, we report significant improvements over state-of-the-art in the task of next-frame prediction.

show abstract

Unsupervised convolutional neural networks for motion estimation

Cited by 2 publications

References 0 publications

Optical Flow Estimation Using a Spatial Pyramid Network

Optical Flow Estimation Using a Spatial Pyramid Network

Hybrid Learning of Optical Flow and Next Frame Prediction to Boost Optical Flow in the Wild

Contact Info

Product

Resources

About