Local Materials Database

Local Materials Database

Kyoto University Computer Vision Lab

This dataset contains images from PASCAL VOC¹, MS COCO², and ImageNet³, which have been supplemented with material region and material segmentation annotations.

Please cite the following work when you use this database in your research:

• Recognizing Material Properties from Images
  G. Schwartz and K. Nishino,
  in IEEE Trans. on Pattern Analysis and Machine Intelligence, 2019.
  [ IEEE Online First ][ project 1 ][ project 2 ]

We provide annotations for examples of the following material categories:

• Asphalt
• Ceramic
• Concrete
• Fabric
• Foliage
• Food
• Glass
• Metal
• Paper
• Plaster
• Plastic
• Rubber
• Soil
• Stone
• Water
• Wood

File Layout

For each image in images/, there will be a mask in masks/{category}/{imagename}_{category}_mask.png for any category annotated in that image. For some masks, there is an additional refinedmask.png version which has been refined using a CRF with manual guidance.

Download

Database

[1] The Pascal Visual Object Classes (VOC) Challenge
Everingham, M. and Van Gool, L. and Williams, C. K. I. and Winn, J. and Zisserman, A.,
in International Journal of Computer Vision, vol. 88, no. 2, 2010.
[2] Microsoft COCO: Common Objects in Context
Lin, Tsung-Yi and Marie, Michael and Belongie, Serge and Hays, James and Perona, Pietro and Ramanan, Deva and Dollar, Piotr and Zitnick, C. Lawrence,
in Proceedings of the European Conference on Computer Vision, 2014.
[3] ImageNet Large Scale Visual Recognition Challenge
Russakovsky, Olga and Deng, Jia and Su, Hao and Krause, Jonathan and Satheesh, Sanjeev and Ma, Sean and Huang, Zhiheng and Karpathy, Andrej and Khosla, Aditya and Bernstein, Michael and Berg, Alexander C. and Fei-Fei, Li,
in International Journal of Computer Vision, vol. 115, no. 3, 2015.