Zobrazeno 1 - 3
of 3
pro vyhledávání: '"Vaishakh Patil"'
Publikováno v:
IEEE Robotics and Automation Letters. 7:3640-3647
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7e03be07186fc2723c12fa8483166784
https://doi.org/10.1109/lra.2022.3146914
https://doi.org/10.1109/lra.2022.3146914
Publikováno v:
CVPR Workshops
We present a self-supervised learning framework to estimate the individual object motion and monocular depth from video. We model the object motion as a 6 degree-of-freedom rigid-body transformation. The instance segmentation mask is leveraged to int
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c95d435fe683016cef412893c24d962f
https://doi.org/10.1109/cvprw50498.2020.00510
https://doi.org/10.1109/cvprw50498.2020.00510
Publikováno v:
IEEE Robotics and Automation Letters, 5 (4)
Autonomous cars need continuously updated depth information. Thus far, depth is mostly estimated independently for a single frame at a time, even if the method starts from video input. Our method produces a time series of depth maps, which makes it a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::822e751132ac6a04e210a05ff3ef0cdb
http://arxiv.org/abs/2001.02613
http://arxiv.org/abs/2001.02613
