BUILDUP: interactive creation of urban scenes from large photo collections

被引:0
作者
Jose Ribelles
Diego Gutierrez
Alyosha Efros
机构
[1] Universitat Jaume I,Institute of New Imaging Technologies
[2] Universidad de Zaragoza,undefined
[3] University of California at Berkeley,undefined
来源
Multimedia Tools and Applications | 2017年 / 76卷
关键词
Image databases; 3D scene composition; Picture generation;
D O I
暂无
中图分类号
学科分类号
摘要
We propose a system for creating images of urban scenes composed of the large structures typical in such environments. Our system provides the user with a precomputed library of image-based 3D objects, such as roads, sidewalks and buildings, obtained from a large collection of photographs. When the user picks the 3D location of a new object to insert, the system retrieves objects that have all the required properties (location, orientation and lighting). Then, the user interface guides the user to add more objects enabling non-experts to make a new composition in a fast and intuitive way. Unlike prior work, the entire image composition process is done in the 3D space of the scene, therefore inconsistent scale or perspective distortion does not arise, and occlusions are properly handled.
引用
收藏
页码:12757 / 12774
页数:17
相关论文
共 39 条
  • [1] Agarwala A(2004)Interactive digital photomontage ACM Trans Graph 23 294-302
  • [2] Dontcheva M(2008)An empirical evaluation of the system usability scale Int J Hum Comput Interact 24 574-594
  • [3] Agrawala M(2013)Internet visual media processing: a survey with graphics and vision applications Vis Comput 29 393-405
  • [4] Drucker S(2006)Semantic photo synthesis Comput Graphics Forum 25 407-413
  • [5] Colburn A(2011)Cg2real: Improving the realism of computer generated images using a large collection of photographs IEEE Trans Vis Comput Graph 17 1273-1285
  • [6] Curless B(2003)Poisson image editing ACM Trans Graph 22 313-318
  • [7] Salesin D(2013)On visual realism of synthesized imagery Proc IEEE 101 1998-2007
  • [8] Cohen M(2008)Labelme: a database and web-based tool for image annotation Int J Comput Vis 77 157-173
  • [9] Bangor A(undefined)undefined undefined undefined undefined-undefined
  • [10] Kortum PT(undefined)undefined undefined undefined undefined-undefined