GRGB-Polarization Glass Segmentation Dataset

Haiyang Mei, Bo Dong, Wen Dong, Jiaxi Yang, Seung-Hwan Baek, Felix Heide, Pieter Peers, Xiaopeng Wei, Xin Yang.

Glass Segmentation using Intensity and Spectral Polarization Cues.

The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2022.

https://openaccess.thecvf.com/content/CVPR2022/html/Mei_Glass_Segmentation_Using_Intensity_and_Spectral_Polarization_Cues_CVPR_2022_paper.html

Please cite this paper when using the data： BibTex.txt

Introduction:

We collected a  large-scale  polarization  glass  segmentation dataset , named RGBP-Glass using a LUCID PHX050S

trichromatic polarizer-array camera that records four different linear-polarization directions (0, 45, 90, and 135 degree) 

for each color channel (i.e., R, G, and B) . RGBP-Glass dataset contains 4511 RGB intensity and corresponding pixel-

aligned trichromatic AoLP and DoLP images . All images come with manually annotated pixel-level accurate reference

glass masks.Each image in RGBP-Glass contains at least one in-the-wild glass object.Our RGBP-Glass dataset offers

rich diversities in scene and glass. Please refer to our paper for detailed statistics of the RGBP-Glass dataset.

As some glass segmentation methods require reflection and edge maps for training, the RGBP-Glass dataset also provides the ground truth associated to these additional information.