TransCut: Transparent Object Segmentation from a Light-Field Image
Yichao Xu, Hajime Nagahara, Atsushi Shimada, Rin-ichiro Taniguchi
Osaka University, Kyushu University, Japan
The segmentation of transparent objects can be very useful in computer vision applications. However, because they borrow texture from their background and have a similar appearance to their surroundings, transparent objects are not handled well by regular image segmentation methods. We propose a method that overcomes these problems using the consistency and distortion properties of a light-field image. Graph-cut optimization is applied for the pixel labeling problem. The light-field linearity is used to estimate the likelihood of a pixel belonging to the transparent object or Lambertian background, and the occlusion detector is used to find the occlusion boundary. We acquire a light field dataset for the transparent object, and use this dataset to evaluate our method. The results demonstrate that the proposed method successfully segments transparent objects from the background.
@inproceedings{transcut_iccv2015,
author = {Yichao Xu and Hajime Nagahara and Atsushi Shimada and Rin-ichiro Taniguchi},
title = {TransCut: Transparent Object Segmentation from a Light-Field Image},
booktitle = {International Conference on Computer Vision (ICCV)},
year = {2015}
}
Dataset
This dataset could be downloaded as a zip file with password protection. To receive the password, please send the release agreement signed by a legal representative of your institution (e.g., your supervisor if you are a student) to the dataset administrator by E-mail: xu(at)ids.osaka-u.ac.jp.