Authors:
Heewon Lee
and
Alper Yilmaz
Affiliation:
Ohio State University, United States
Keyword(s):
Photo consistency, Homography, 3D Recovery
Related
Ontology
Subjects/Areas/Topics:
Applications
;
Computer Vision, Visualization and Computer Graphics
;
Geometry and Modeling
;
Image and Video Analysis
;
Image Formation and Preprocessing
;
Image-Based Modeling
;
Multi-View Geometry
;
Pattern Recognition
;
Software Engineering
;
Surface Geometry and Shape
Abstract:
This paper presents a new 3D object shape reconstruction approach, which exploits the homography transform and photo consistency between multiple images. The proposed method eliminates the requirement of dense feature correspondences, camera calibration, and pose estimation. Using planar homography, we generate a set of planes slicing the object to a set of parallel cross-sections in the 3D object space. For each object slice, we check photo consistency based on color observation. This approach in return provides us with the capability for expressing convex and concave parts of the object. We show that the application of our approach to a standard multiple view dataset achieves comparably better performance than competing silhouette based method.