Light Field Convergency: Implicit Photometric Consistency on Transparent Surface

Yuta Ideguchi, Yuki Uranishi, Shunsuke Yoshimoto, Yoshihiro Kuroda, Osamu Oshiro; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 41-49

Abstract


This paper proposes a method for estimating the surface oftransparentobjectsbasedonlightfieldconvergency. The lightfieldconvergencyrepresentsthedegreeofconvergence ofthelightfieldateachpoint. Theproposedmethodutilizes local photo consistency, which is one of characteristics of the light field convergency. Around a boundary contour, a point that is visible from viewpoints with a small convergence angle is locally consistent. In other words, the local photo consistency is implicitly maintained near the boundary contour. We use a light field camera as a camera array withsmallconvergenceanglestoestimatethesurfaceofthe transparentobject. Experimentalresultshavedemonstrated thatthedepthofthetransparentobjectisestimatedfromthe captured image by the light field camera.

Related Material


[pdf]
[bibtex]
@InProceedings{Ideguchi_2017_CVPR_Workshops,
author = {Ideguchi, Yuta and Uranishi, Yuki and Yoshimoto, Shunsuke and Kuroda, Yoshihiro and Oshiro, Osamu},
title = {Light Field Convergency: Implicit Photometric Consistency on Transparent Surface},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}