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
Check out the new #paper by the team at @EdinburghUni on "3D plane labeling #stereo #matching" https://t.co/PvatuaAjko #3dvision @EU_H20202 weeks
A new #contribution to the project from @EdinburghUni team. Check it out https://t.co/cqjQwtfUNw #robotics #vision @EU_H2020 @EUScienceInnov3 weeks
#GroundTruth recording in the #garden at @WUR. Stay tuned for the #dataset releases :) #3d #reconstruction #vision https://t.co/7uyOXpCDy44 weeks
RT @EU_H2020: #FF #H2020 @CARISMAND @InVID_EU @iMETland @RADARCNS @RESCEUproject @PAL4Uproject @BAMB2020 @AdaptSmartIMI @sparks_eu…4 weeks
"Embedded Real-time Multi-Baseline Stereo" #contribution at #ICRA17 by our partners @ETH_en https://t.co/1nIkJYxXX44 weeks