1. [Publications](/index.php/publications) 2. Semantic Video CNNs through Representation Warping # Semantic Video CNNs through Representation Warping ![](/sites/default/files/styles/wide/public/publications/teaser_fig2_0.png?itok=sHR2vgw7) In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very little extra computational cost. This module is called NetWarp and we demonstrate its use for a range of network architectures. The main design principle is to use optical flow of adjacent frames for warping internal network representations across time. A key insight of this work is that fast optical flow methods can be combined with many different CNN architectures for improved performance and end-to-end training. Experiments validate that the proposed approach incurs only little extra computational cost, while improving performance, when video streams are available. We achieve new state-of-the-art results on the CamVid and Cityscapes benchmark datasets and show consistent improvements over different baseline networks. Our code and models are available at . ## Authors Raghudeep Gadde (Max Planck ETH Center for Learning Systems) Varun Jampani (NVIDIA) Peter V. Gehler (Amazon) ## Publication Date Sunday, October 22, 2017 ## Published in [International Conference on Computer Vision (ICCV'17)](http://iccv2017.thecvf.com) ## Research Area [Computer Vision](/index.php/research-area/computer-vision) ## External Links [pdf](https://varunjampani.github.io/papers/gadde17_ICCV.pdf) [video](https://youtu.be/T6gq5wMaxAo) ## Copyright This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to .