Ambient Point Clouds for View Interpolation
M. Goesele, J. Ackermann, S. Fuhrmann, C. Haubold, R. Klowsky, D. Steedly, R. Szeliski
Abstract
View interpolation and image-based rendering algorithms often produce visual artifacts in regions where the 3D scene geometry is erroneous, uncertain, or incomplete. We introduce ambient point clouds constructed from colored pixels with uncertain depth, which help reduce these artifacts while providing non-photorealistic background coloring and emphasizing reconstructed 3D geometry. Ambient point clouds are created by randomly sampling colored points along the viewing rays associated with uncertain pixels. Our real-time rendering system combines these with more traditional rigid 3D point clouds and colored surface meshes obtained using multi-view stereo. Our resulting system can handle larger-range view transitions with fewer visible artifacts than previous approaches.
Literature, Movie, Data
- Ambient Point Clouds for View Interpolation
Michael Goesele, Jens Ackermann, Simon Fuhrmann, Carsten Haubold, Ronny Klowsky, Drew Steedly, Richard Szeliski
In: ACM Transactions on Graphics (Proceedings of ACM SIGGRAPH 2010), Los Angeles, USA, July 25-29, ACM, New York, 2010 - Movie: Ambient Point Clouds for View Interpolation (MP4, approx. 150MB)
- Hanau dataset used in the paper (147 images), courtesy of Rolf Kruse and Cornelius Weidner, Invirt GmbH