Visual Material Traits: Trait Annotations

Kyoto University Computer Vision Lab

Visual material traits are locally-recognizable visual properties corresponding to characteristic material appearances. We have shown that these material traits can be used to identify materials based solely on locally-available image features.

We have augmented the Flickr Materials Database (FMD) of Sharan et al.1 with binary mask annotations for 13 visual material traits. We have used these annotations to learn visual material traits and, later, to evaluate automatically discovered local material attributes. We consistently annotated FMD images with material trait masks that highlight only local regions indiciative of each trait.


Woven                 Shiny

Striped             Metallic
Liquid                 Fuzzy

The traits we use in our dataset are:

  • Fuzzy
  • Shiny
  • Smooth
  • Soft
  • Striped
  • Metallic
  • Organic
  • Translucent
  • Transparent
  • Rough
  • Liquid
  • Woven
  • Manmade

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

  • Automatically Discovering Local Visual Material Attributes
    G. Schwartz and K. Nishino,
    in Proc. of IEEE Conference on Computer Vision and Pattern Recognition CVPR’15, Jun., 2015.
    [ paper ][ project ]

  • Visual Material Traits: Recognizing Per-Pixel Material Context
    G. Schwartz and K. Nishino,
    in Proc. of Color and Photometry in Computer Vision (Workshop held in conjunction with ICCV’13), Dec., 2013.
    [ paper ][ database ][ project ]

File Layout

Trait masks are stored in directories corresponding to the trait name. The filename of each mask corresponds to the original image in the FMD, simply replace the ‘.png’ extension with ‘.jpg’.

Layout (files inside fmd_traits.tgz):
  • trait_annotations/
    • ${trait_name}/
      • ${fmd_image_prefix}.png – Binary mask for ${trait_name} in
        ${fmd}/image/${category}/${fmd_image_prefix}.jpg

Download

Trait Annotations

[1] Material perception: What can you see in a brief glance?
L. Sharan, R. Rosenholtz, and E.H. Adelson,
Journal of Vision, vol. 14, no. 9, article 12, 2014.
[ Database ]