2015年4月26日 · In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations.

2016年12月6日 · FlowNet 2.0 yields smooth flow fields, preserves fine motion details and runs at 8 to 140fps. The accuracy on this example is four times higher than with the original FlowNet. …

Pytorch implementation of FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks. Multiple GPU training is supported, and the code provides examples for training or inference on MPI-Sintel clean and final datasets.

2016年12月6日 · Particularly on small displacements and real-world data, FlowNet cannot compete with variational methods. In this paper, we advance the concept of end-to-end learning of optical flow and make it work really well.

In this paper, we propose training CNNs end-to-end to learn predicting the optical flow field from a pair of images. While optical flow estimation needs precise per-pixel lo-calization, it also …

In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic architecture and another one including a layer that correlates feature vectors at different image locations.

Two neural network models are currently provided, along with their batch norm variation (experimental) : Thanks to Kaixhin you can download a pretrained version of FlowNetS (from caffe, not from pytorch) here. This folder also contains trained networks from scratch.

2015年4月26日 · In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: a generic...

In this paper we construct appropriate CNNs which are capable of solving the optical flow estimation problem as a supervised learning task. We propose and compare two architectures: …

FlowNet 2.0 is only marginally slower than the original FlowNet but decreases the estimation error by more than 50%. It performs on par with state-of-the-art methods, while running at interactive frame rates. Moreover, we present faster variants that al-low optical flow computation at up to 140fps with accuracy matching the original FlowNet. 1.