Author:
Dimitri Bulatov
Affiliation:
Fraunhofer Institute of Optronics and System Technologies and Image Exploitation, Germany
Keyword(s):
Aggregation Function, Interaction Set, Depth map, Plane Sweep, Triangle Mesh.
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Device Calibration, Characterization and Modeling
;
Geometry and Modeling
;
Image and Video Analysis
;
Image Formation and Preprocessing
;
Image Registration
;
Image-Based Modeling
;
Motion, Tracking and Stereo Vision
;
Pattern Recognition
;
Shape Representation and Matching
;
Software Engineering
;
Stereo Vision and Structure from Motion
Abstract:
Obtaining accurate depth maps from multi-view configurations is an essential component for dense scene reconstruction from images and videos. In the first part of this paper, a plane sweep algorithm for sampling an energy function for every depth label and a dense set of points is presented. The distinctive features of this algorithm are 1) that despite a flexible model choice for the underlying geometry and radiometry, the energy function is performed by merely image operations instead of pixel-wise computations, and 2) that it can be easily manipulated by different terms, such as triangle-based smoothing term, or post-processed by one of the numerous state-of-the-art non-local energy minimization algorithms. The second contribution of this paper is a search for optimal ways to aggregate multiple observations in order to make the cost function more robust near the image border and in occlusions areas. Experiments with different data sets show the relevance of the proposed research,
emphasize the potential of the algorithm, and provide ideas of future work.
(More)