完整後設資料紀錄
DC 欄位語言
dc.contributor.authorWang, Tsun-Hsuanen_US
dc.contributor.authorWang, Fu-Enen_US
dc.contributor.authorLin, Juan-Tingen_US
dc.contributor.authorTsai, Yi-Hsuanen_US
dc.contributor.authorChiu, Wei-Chenen_US
dc.contributor.authorSun, Minen_US
dc.date.accessioned2020-01-02T00:03:29Z-
dc.date.available2020-01-02T00:03:29Z-
dc.date.issued2019-01-01en_US
dc.identifier.isbn978-1-5386-6026-3en_US
dc.identifier.issn1050-4729en_US
dc.identifier.urihttp://hdl.handle.net/11536/153338-
dc.description.abstractWe propose a novel plug-and-play (PnP) module for improving depth prediction with taking arbitrary patterns of sparse depths as input. Given any pre-trained depth prediction model, our PnP module updates the intermediate feature map such that the model outputs new depths consistent with the given sparse depths. Our method requires no additional training and can be applied to practical applications such as leveraging both RGB and sparse LiDAR points to robustly estimate dense depth map. Our approach achieves consistent improvements on various state-of-the-art methods on indoor (i.e., NYU-v2) and outdoor (i.e., KITTI) datasets. Various types of LiDARs are also synthesized in our experiments to verify the general applicability of our PnP module in practice.en_US
dc.language.isoen_USen_US
dc.titlePlug-and-Play: Improve Depth Prediction via Sparse Data Propagationen_US
dc.typeProceedings Paperen_US
dc.identifier.journal2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)en_US
dc.citation.spage5880en_US
dc.citation.epage5886en_US
dc.contributor.department交大名義發表zh_TW
dc.contributor.departmentNational Chiao Tung Universityen_US
dc.identifier.wosnumberWOS:000494942304042en_US
dc.citation.woscount0en_US
顯示於類別:會議論文