Transcription of HITNet: Hierarchical Iterative Tile Refinement Network for ...
{{id}} {{{paragraph}}}
HITNet: Hierarchical Iterative Tile Refinement Network for Real-time StereoMatchingVladimir TankovichChristian H aneYinda ZhangAdarsh KowdleSean FanelloSofien BouazizGoogle{vtankovich, chaene, yindaz, adarshkowdle, seanfa, 1: Example result of HITNet on the SceneFlow, KITTI, ETH3D and Middlebury datasets. Our approach predictsaccurate depth with crisp edges. HITNet obtains state-of-art results on KITTI, ETH3D and Middlebury-v3 paper presents HITNet, a novel neural Network ar-chitecture for real-time stereo matching. Contrary to manyrecent neural Network approaches that operate on a full costvolume and rely on 3D convolutions, our approach does notexplicitly build a volume and instead relies on a fast multi-resolution initialization step, differentiable 2D geometricpropagation and warping mechanisms to infer disparity hy-potheses.}
rately perform geometric warping and upsampling opera-tions. Our architecture is inherently multi-resolution allow- ... ing real-time performance. Fast approaches [25, 60] down- ... tional stereo matching methods [43]. In particular, we ob-serve that recent efficient methods rely on the three follow-ing steps:
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document:
{{id}} {{{paragraph}}}