Paper
23 June 2003 Spatio-temporal view interpolation in real-time
Author Affiliations +
Proceedings Volume 5150, Visual Communications and Image Processing 2003; (2003) https://doi.org/10.1117/12.503050
Event: Visual Communications and Image Processing 2003, 2003, Lugano, Switzerland
Abstract
An algorithm is presented to view interpolation of dynamic events in real-time across time and space. Two temporal and two spatial flow fields are estimated from four images captured by two cameras at two different times. Hybrid gradient- and correlation-based motion estimation is used to compute optical flow fields with high density and accuracy. Based on the flow fields, texture coordinates of small textured squares are computed and a new image is composed at an arbitrary viewpoint and time. Real-time processing is possible through vectorized implementation of computational demanding functions and visualization using OpenGL and standard graphics hardware. The spatio-temporal view interpolation algorithm is applicable to non-rigid events, does not use explicit 3D models, and requires no user input.
© (2003) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Torsten Radtke "Spatio-temporal view interpolation in real-time", Proc. SPIE 5150, Visual Communications and Image Processing 2003, (23 June 2003); https://doi.org/10.1117/12.503050
Lens.org Logo
CITATIONS
Cited by 1 scholarly publication.
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Cameras

Motion estimation

Visualization

Optical flow

Data conversion

Optical filters

OpenGL

RELATED CONTENT

Monocular visual odometry-based 3D-2D motion estimation
Proceedings of SPIE (February 19 2018)
Video indexing using motion vectors
Proceedings of SPIE (November 01 1992)
Visual road following without 3D reconstruction
Proceedings of SPIE (February 25 1994)

Back to Top