Example-based photometric stereo: shape reconstruction with general, varying BRDFs

By Aaron Hertzmann, S. M. Seitz. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005

333 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.

3-D Depth Reconstruction from a Single Still Image (2007, background): “Hertzmann et al. [17] reconstructed high quality 3-d models from several images, but they required that the images also contain “assistant” objects of known shapes next to the target object.”
Evaluation of Stereo Matching Costs on Images with Radiometric Differences (2009, unknown): “However, multiple images can also be used for explicitly modeling non-Lambertian scenes [26], [27], [28] or reflections [29].”
Retrographic sensing for the measurement of surface texture and shape (2009, methodology): “The main disadvantage is the need for a calibration object with the same reﬂectance properties as the object being modeled—this requirement could be met with paint, but otherwise seemed too restrictive for modeling natural materials.”
Multi-View Stereo: A Tutorial (2015, background): “e, dark room with a controllable point light source) [96, 28, 27, 107].”
Dynamic shape capture using multi-view photometric stereo (2009, methodology): “The presented data-driven method shares some similarities with [Hertzmann and Seitz 2005], where an object of known geometry is used to assist in determining photometric normals.”