Shape and Spatially-Varying BRDFs from Photometric Stereo

By Dan B. Goldman, Brian Curless, Aaron Hertzmann, S. M. Seitz. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010

414 citations recorded by the source corpus.

How researchers see this paper

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

Retrographic sensing for the measurement of surface texture and shape (2009, methodology): “The active systems are the most successful at this time, and they can be quite versatile and accurate [3, 8, 7].”
NeRD: Neural Reflectance Decomposition from Image Collections (2020, background): “Capturing the geometry and material properties of an object is essential for several computer vision and graphics applications such as view synthesis [10, 56], relighting [5, 10, 22, 23, 32, 57], object insertion [7, 21, 32] etc .”
KNN Matting (2013, neutral): “Blending weights are available in [11], where an SVBRDF was decomposed into specular and diffuse basis components that are homogeneous, as previously done in [7].”
Estimating image depth using shape collections (2014, methodology): “This problem is ill-posed when the input is a single image, and existing approaches typically incorporate additional information such as user interaction [Wu et al. 2008] and shading [Lensch et al. 2003; Goldman et al. 2005], or using abstracted proxy shapes [Zheng et al. 2012].”