SEARCH SESSIONS

Search All
 
Refine Results:
 
Year(s)

SOCIAL MEDIA

EMAIL SUBSCRIPTION

 
 

GTC ON-DEMAND

Computer Vision
Presentation
Media
GPU Driven Dense Reconstruction for Community Photo Collections
Speakers:
Jan-Michael Frahm
- University of North Carolina, Chapel Hill
Abstract:
We present a system to reconstruct dense 3D models from community photo collections. First images are described using GIST and are clustered using hamming distances. Each of these clusters is geometrically verified and connected using Geotags. Connected clusters are bundle adjusted and the obtained registration is used to estimate depthmaps that are finally fused to obtain dense 3D models. Each of the above steps, except Bundle Adjustment, is implemented in CUDA and runs on multiple GPUs . The performance of our pipeline is two order of magnitude faster on one order more images compared to state of the art method.
 
Topics:
Computer Vision
Type:
Poster
Event:
GTC Silicon Valley
Year:
2010
Session ID:
P10F09
Download:
Share: