FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
-
Updated
Oct 9, 2018 - Python
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks
Google Colab notebook for running Nvidia flownet2-pytorch
Consist of four different approaches for generating optical flow and can be demonstrated in Colab.
Dockerized fast-artistic-videos
In this repository, we deal with the task of video frame interpolation with estimated optical flow. To estimate the optical flow we use pre-trained FlowNet2 deep learning model and experiment by fine-tuning it. We explore the interpolation performance on Spheres dataset and Corridor dataset.
Video Super Resolution with depth map and optical flow for unnatural object flow
Pytorch implementation of our method for high-resolution (e.g. 2048x1024) photorealistic video-to-video translation.
Improve performance of PWC-Net in foggy scenes
CrackPropNet
Add a description, image, and links to the flownet2 topic page so that developers can more easily learn about it.
To associate your repository with the flownet2 topic, visit your repo's landing page and select "manage topics."