Dynamic seethroughs: Synthesizing hidden views of moving objects

This paper presents a method to create an illusion of seeing moving objects through occluding surfaces in a video. This illusion is achieved by transferring information from a camera viewing the occluded area. In typical view interpolation approaches for 3D scenes, some form of correspondence across views is required. For occluded areas, establishing direct correspondence is impossible as information is missing in one of the views. Instead, we use a 2D projective invariant to capture information about occluded objects (which may be moving). Since invariants are quantities that do not change across views, a visually compelling rendering of hidden areas is achieved without the need for explicit correspondences. A piece-wise planar model of the scene allows the entire rendering process to take place without any 3D reconstruction, while still producing visual parallax. Because of the simplicity and robustness of the 2D invariant, we are able to transfer both static backgrounds and moving objects in real time. A complete working system has been implemented that runs live at 5Hz. Applications for this technology include the ability to look through corners at tight intersections for automobile safety, concurrent visualization of a surveillance camera network, and monitoring systems for patients/elderly/children.

[1]  Yuichi Ohta,et al.  NAVIVIEW : BIRD'S-EYE VIEW FOR DRIVERS USING ROADSIDE CAMERAS , 1999 .

[2]  Richard Szeliski,et al.  The lumigraph , 1996, SIGGRAPH.

[3]  Andrew Lippman,et al.  Movie-maps: An application of the optical videodisc to computer graphics , 1980, SIGGRAPH '80.

[4]  Leonard McMillan,et al.  Plenoptic Modeling: An Image-Based Rendering System , 2023 .

[5]  Steven M. Seitz,et al.  View morphing , 1996, SIGGRAPH.

[6]  Antonio Criminisi,et al.  Creating Architectural Models from Images , 1999, Comput. Graph. Forum.

[7]  Alex Pentland,et al.  Pfinder: Real-Time Tracking of the Human Body , 1997, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Lance Williams,et al.  View Interpolation for Image Synthesis , 1993, SIGGRAPH.

[9]  Christian Sandor,et al.  Improving Spatial Perception for Augmented Reality X-Ray Vision , 2009, 2009 IEEE Virtual Reality Conference.

[10]  Bernhard P. Wrobel,et al.  Multiple View Geometry in Computer Vision , 2001 .

[11]  Steven M. Seitz,et al.  Photo tourism: exploring photo collections in 3D , 2006, ACM Trans. Graph..

[12]  Suya You,et al.  3D video surveillance with Augmented Virtual Environments , 2003, IWVS '03.

[13]  Deborah Hix,et al.  A Perceptual Matching Technique for Depth Judgments in Optical, See-Through Augmented Reality , 2006, IEEE Virtual Reality Conference (VR 2006).

[14]  I. Kitahara,et al.  Live mixed-reality 3D video in soccer stadium , 2003, The Second IEEE and ACM International Symposium on Mixed and Augmented Reality, 2003. Proceedings..

[15]  Jitendra Malik,et al.  Modeling and Rendering Architecture from Photographs: A hybrid geometry- and image-based approach , 1996, SIGGRAPH.

[16]  Yuichi Ohta,et al.  Outdoor see-through vision utilizing surveillance cameras , 2004, Third IEEE and ACM International Symposium on Mixed and Augmented Reality.

[17]  P. Debevec,et al.  Image-based modeling, rendering, and lighting , 2002, IEEE Computer Graphics and Applications.