Holistic 3D scene understanding from a single geo-tagged image
作者： Shenlong Wang , Sanja Fidler , Raquel Urtasun
DOI: 10.1109/CVPR.2015.7299022
关键词:
摘要: In this paper we are interested in exploiting geographic priors to help outdoor scene understanding. Towards goal propose a holistic approach that reasons jointly about 3D object detection, pose estimation, semantic segmentation as well depth reconstruction from single image. Our takes advantage of large-scale crowd-sourced maps generate dense geographic, geometric and by rendering the world. We demonstrate effectiveness our model on challenging KITTI dataset [13], show significant improvements over baselines all metrics tasks.
sci-hub.se 参考文章(45)
Christian Hane, Nikolay Savinov, Marc Pollefeys, Class Specific 3D Object Shape Priors Using Surface Normals computer vision and pattern recognition. pp. 652- 659 ,(2014) , 10.1109/CVPR.2014.89
Antonio Torralba, Kevin P. Murphy, William T. Freeman, Sharing Visual Features for Multiclass and Multiview Object Detection IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 29, pp. 854- 869 ,(2007) , 10.1109/TPAMI.2007.1055
K.M.G. Cheung, S. Baker, T. Kanade, Shape-from-silhouette of articulated objects and its use for human body kinematics estimation and motion capture computer vision and pattern recognition. ,vol. 1, pp. 77- 84 ,(2003) , 10.1109/CVPR.2003.1211340
P F Felzenszwalb, R B Girshick, D McAllester, D Ramanan, Object Detection with Discriminatively Trained Part-Based Models IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 32, pp. 1627- 1645 ,(2010) , 10.1109/TPAMI.2009.167
Varsha Hedau, Derek Hoiem, David Forsyth, Recovering the spatial layout of cluttered rooms international conference on computer vision. pp. 1849- 1856 ,(2009) , 10.1109/ICCV.2009.5459411
Lubomir Bourdev, Jitendra Malik, Poselets: Body part detectors trained using 3D human pose annotations international conference on computer vision. pp. 1365- 1372 ,(2009) , 10.1109/ICCV.2009.5459303
Angeline Loh, The recovery of 3-D structure using visual texture patterns ,(2006)
Philipp Kraehenbuehl, Vladlen Koltun, Parameter Learning and Convergent Inference for Dense Random Fields international conference on machine learning. pp. 513- 521 ,(2013)
Nathan Silberman, Derek Hoiem, Pushmeet Kohli, Rob Fergus, Indoor Segmentation and Support Inference from RGBD Images Computer Vision – ECCV 2012. pp. 746- 760 ,(2012) , 10.1007/978-3-642-33715-4_54
E. Prados, O. Faugeras, Shape From Shading Handbook of Mathematical Models in Computer Vision. pp. 375- 388 ,(2006) , 10.1007/0-387-28831-7_23