Scientific contributions

FlowNet 2.0 @CVPR 2017

FlowNet 2.0 is the first optical flow approach based on deep learning that reaches state-of-the-art accuracy. At the same time it is by a factor 100 faster than previous state-of-the-art techniques. This allows for reliable motion estimation at interactive frame rates. For more information visit the paper page.

Read More

DeMoN @CVPR 2017

DeMoN is the very first work that formulates the problem of joint egomotion and depth estimation as a pure learning problem. Given two images from a single moving camera, DeMoN can estimate depth and camera motion at interactive frame rates. For more information, please visit the website.

Read More
Twitter
@butterflock It is back online :)11 months
@butterflock Hi, we are migrating the servers and expect to be back online with our git repositories next week. Thanks!11 months
The Push-Pull layer was developed within our project and the code is now available #MachineLearning #ConvNets… https://t.co/sviIgOnEzr11 months
TrimBot2020 Final Demonstration: Mobile Vehicle Localisation and Trimming https://t.co/VgdXLB6Bei via @YouTube1 year
RT @trimbot2020: @ETH @EdinburghUni @univgroningen @UniFreiburg @UvA_Amsterdam @WUR @BoschGlobal Behind the research are real people - and…1 year