Title :
Refractive height fields from single and multiple images
Author :
Shan, Qi ; Agarwal, Sameer ; Curless, Brian
Author_Institution :
Univ. of Washington, Seattle, WA, USA
Abstract :
We propose a novel framework for reconstructing homogenous, transparent, refractive height-fields from a single viewpoint. The height-field is imaged against a known planar background, or sequence of backgrounds. Unlike existing approaches that do a point-by-point reconstruction - which is known to have intractable ambiguities - our method estimates and optimizes for the entire height-field at the same time. The formulation supports shape recovery from measured distortions (deflections) or directly from the images themselves, including from a single image. We report results for a variety of refractive height-fields showing significant improvement over prior art.
Keywords :
computer vision; image reconstruction; computer vision; homogenous height-fields; multiple images; point-by-point reconstruction; refractive height fields; refractive height-fields; shape recovery; single images; transparent height-fields; Cameras; Glass; Image reconstruction; Indexes; Optimization; Shape; Surface reconstruction;
Conference_Titel :
Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on
Conference_Location :
Providence, RI
Print_ISBN :
978-1-4673-1226-4
Electronic_ISBN :
1063-6919
DOI :
10.1109/CVPR.2012.6247687