Reflectance and texture of real-world surfaces

By Kristin J. Dana, B. van Ginneken, Shree K. Nayar, Jan J. Koenderink. 1999

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

COCO-Stuff: Thing and Stuff Classes in Context (2016, background): “Early stuff datasets [6, 15, 34, 9] focused on texture classification and had simple images completely covered with a single textured patch.”
Describing Textures in the Wild (2013, methodology): “Texture classification has been widely studied in the context of recognizing materials supported by datasets such as CUReT [9], UIUC [18], UMD [39], Outex [23], Drexel Texture Database [24], and KTH-TIPS [7, 14].”
Material recognition in the wild with the Materials in Context Database (2014, methodology): “For instance, the CUReT [4] database contains 61 material samples, each captured under 205 different lighting and viewing conditions.”
A Statistical Approach to Material Classification Using Image Patch Exemplars (2009, methodology): “In this section, we describe the Columbia-Utrecht (CUReT) database [10] and its level of difﬁculty for single image classiﬁcation.”
OpenSurfaces (2013, methodology): “…including the MERL database [Matusik et al. 2003] with 4D BRDF measurements for 105 materials, fit to various BRDF models [Ngan et al. 2005], and CUReT [Dana et al. 1999], with 6D measured BTFs (bidirectional texture functions) for 61 samples with various lighting and illumination conditions.”
Class-specific material categorisation (2005, background): “Variants of LBP have been introduced to provide rotational invariance, and also to reduce the effect of random noise (the uniform LBP) [20].”
Example-based photometric stereo: shape reconstruction with general, varying BRDFs (2005, background): “Another interesting avenue for future research is to remove the need for a physical reference object by rendering a synthetic one, given a known lighting environment and a known BRDF model (e.g., [8]).”
The 3D Model Acquisition Pipeline (2002, background): “[105] observed that even full BRDF and normals maps are not adequate for capturing the change in detail surface appearance with lighting and view for surfaces with fine scale geometric complexity such as bread and velvet.”
Deep Filter Banks for Texture Recognition, Description, and Segmentation (2015, background): “CUReT [29] (5612 images, 61 classes), UIUC [57] (1000 images, 25 classes), KTH-TIPS [17] (810 images, 10 classes) are collected in controlled conditions, by photographing the same instance of a material, under varying scale, viewing angle and illumination.”