Volumetric Correspondence Networks
for Optical Flow
Gengshan Yang1 , Deva Ramanan1,2
1
Carnegie Mellon University, 2 Argo AI
{gengshay, deva}@cs.cmu.edu
Abstract
Many classic tasks in vision – such as the estimation of optical flow or stereo
disparities – can be cast as dense correspondence matching. Well-known techniques
for doing so ma ...


雷达卡



京公网安备 11010802022788号







