BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Large-Scale Camera Pose Voting and the Geometric Burstiness Proble
 m - Dr Torsten Sattler is a Postdoctoral Researcher at the Computer Vision
  and Geometry (CVG) Group of the Institute for Visual Computing of the Dep
 artment of Computer Science&gt\; at ETH Zurich headed by Prof. Marc Pollef
 eys.  Dr Sattler is working on the V-C
DTSTART:20160418T100000Z
DTEND:20160418T110000Z
UID:TALK65581@talks.cam.ac.uk
CONTACT:Geraldine Duggan
DESCRIPTION:Location recognition is the problem of determining the place d
 epicted in a given photo. In the first part of the talk\, we consider the 
 case where the scene is represented by a 3D model and we are not only inte
 rested in the place depicted in an image but also the position and orienta
 tion from which the image was taken\, i.e.\, the camera pose. A major chal
 lenge for solving this image-based localization problem is to establish th
 e 2D-3D matches required for pose estimation. This is especially true for 
 large scale scenes containing many 3D points with similar local appearance
 . Instead of using elaborate matching schemes\, we introduce an efficient 
 camera voting approach whose run-time is independent of the inlier ratio. 
 While our approach allows us to handle an arbitrary number of matches in l
 inear time\, we show that simply increasing the number of 2D-3D matches us
 ed for pose estimation does not solve the image-based localization problem
 . The reason for this behavior is that increasing the\n\nnumber of matches
  leads to wrong poses with many inliers. In the second part of the talk\, 
 we thus consider the problem of finding a better decision criterion than t
 he raw inlier count. We show that geometric bursts\, i.e.\, spatial config
 urations appearing at multiple places in a scene\, are a major reason why 
 the raw inlier count fails for large-scale location recognition. We introd
 uce simple schemes that allow us to efficiently detect geometric bursts du
 ring query time. We show experimentally that down-weighting inliers based 
 on the number of bursts they appear in allows us to better decide between 
 correct and incorrect place recognition results and significantly boosts t
 he location recognition performance.\n
LOCATION:Cambridge University Engineering Department\, Lecture Room number
  LR11
END:VEVENT
END:VCALENDAR