3D Reconstruction Using Photo Consistency From Uncalibrated Multiple Views

Date Added: May 2010
Format: PDF

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 for dense feature correspondences, camera calibration, and pose estimation. Using planar homography, the authors generate a set of planes slicing the object to a set of parallel cross-sections in the 3D object space. For each object slice, the authors check photo consistency based on color observation. This approach in return provides them with the capability for expressing convex and concave parts of the object. This paper shows that the application of the approach to a standard multi-view dataset achieves comparably better performance than competing silhouette based method.