{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T10:14:37Z","timestamp":1776334477952,"version":"3.51.2"},"reference-count":30,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/cvpr.2015.7298715","type":"proceedings-article","created":{"date-parts":[[2015,10,15]],"date-time":"2015-10-15T18:42:06Z","timestamp":1444934526000},"page":"1119-1127","source":"Crossref","is-referenced-by-count":143,"title":["Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs"],"prefix":"10.1109","author":[{"family":"Bo Li","sequence":"first","affiliation":[]},{"family":"Chunhua Shen","sequence":"additional","affiliation":[]},{"family":"Yuchao Dai","sequence":"additional","affiliation":[]},{"given":"Anton","family":"van den Hengel","sequence":"additional","affiliation":[]},{"family":"Mingyi He","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.421"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0071-y"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.97"},{"key":"ref12","first-page":"468","article-title":"Discriminatively trained dense surface normal estimation","author":"ladick","year":"2014","journal-title":"Proc Eur Conf Comp Vis"},{"key":"ref13","first-page":"775","article-title":"Depth extraction from video using non-parametric sampling","author":"karsch","year":"2012","journal-title":"Proc Eur Conf Comp Vis"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2012.6238903"},{"key":"ref15","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref16","article-title":"Depth estimation using monocular and stereo cues","volume":"7","author":"saxena","year":"2007","journal-title":"Proc IEEE Int Joint Conf Artificial Intell"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.19"},{"key":"ref19","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"eigen","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"ref4","first-page":"746","article-title":"Indoor segmentation and support inference from rgbd images","author":"silberman","year":"2012","journal-title":"Proc Eur Conf Comp Vis"},{"key":"ref27","first-page":"71","article-title":"Patch based synthesis for single depth image super-resolution","author":"mac","year":"2012","journal-title":"Proc Eur Conf Comp Vis"},{"key":"ref3","first-page":"86","article-title":"Learning to be a depth camera for close-range human capture and interaction","volume":"33","author":"fanello","year":"2014","journal-title":"ACM T Graphics"},{"key":"ref6","first-page":"687","article-title":"Unfolding an indoor origami world","author":"fouhey","year":"2014","journal-title":"Proc Eur Conf Comp Vis"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref5","first-page":"482","article-title":"Blocks world revisited: Image understanding using qualitative geometry and mechanics","author":"gupta","year":"2010","journal-title":"Proc Eur Conf Comp Vis"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995551"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/34.784284"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2398356.2398381"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.132"},{"key":"ref1","first-page":"2759","article-title":"RDB-D scene labeling: Features and algorithms","author":"ren","year":"2012","journal-title":"Proc IEEE Conf Comp Vis Patt Recogn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref22","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref21","article-title":"Learning and transferring mid-level image representations using convolutional neural networks","author":"oquab","year":"2013","journal-title":"Proc IEEE Conf Comp Vis Patt Recogn"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459175"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1080\/757582976"},{"key":"ref26","first-page":"291","article-title":"An application of markov random fields to range sensing","author":"diebel","year":"2005","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015780"}],"event":{"name":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Boston, MA, USA","start":{"date-parts":[[2015,6,7]]},"end":{"date-parts":[[2015,6,12]]}},"container-title":["2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7293313\/7298593\/07298715.pdf?arnumber=7298715","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,24]],"date-time":"2017-03-24T17:52:46Z","timestamp":1490377966000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7298715\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/cvpr.2015.7298715","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}