personal
Google
CG
recaptured CG
Figure 1: Examples from our image sets. Note the photorealism of all
images.
(a) Computer Graphics
Architecture (295)
Game (41)
Nature (181)
Object (220)
Life (50)
Hybrid (13)
Indoor-light (40)
Indoor-dark (38)
Outdoor-rain (63) Outdoor-night (26)
Outdoor-day (76) Outdoor-dusk (29)
Natural-obj (62)
Artificial-obj (66)
(b) Authors Personal
Figure 2: (a) Subcategories within the PRCG image set and (b) Subcate-
gories within Personal image set, the number is the image count.
3 A Overview of the Columbia Photographic Im-
ages and Photorealistic Computer Graphics Dataset
We have designed and implemented the Columbia Photographic Images and
Photorealistic Computer Graphics Dataset in accordance to the criteria men-
tioned in Section 2. The dataset is used in our work for the classification of
PIM and PRCG [21]. The dataset consists of four sets of images, as shown
in Figure 1 and briefly described below. A detailed description would be
given in the subsequent sections.
1. 800 PRCG images from the Internet (PRCG): These images
are categorized by content into architecture, game, nature, object
and life, see Figure 2(a). The PRCG are mainly collected from 40
3D-graphics websites, such as www.softimage.com, www.3ddart.org,
www.3d-ring.com and so on. The rendering software used are such
as 3ds MAX, softimage-xsi, Maya, Terragen and so on. The geometry
modelling tools used include AutoCAD, Rhinoceros, softimage-3D and
so on. The high-end rendering techniques used include global illumi-
nation with ray tracing or radiosity, simulation of the camera depth-of-
5