Computing Local Surface Orientation and Shape from Texture for Curved Surfaces

How researchers see this paper

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

Make3D: Learning 3D Scene Structure from a Single Still Image (2009, methodology): “Examples i nclude shape-from-shading [12], [13] and shape-from-textu r [14], [15]; however, these methods are difficult to apply to surfac es that do not have fairly uniform color and texture.”
3-D Depth Reconstruction from a Single Still Image (2007, background): “Methods such as shape from shading [12; 13] and shape from texture [14; 15 ; 16] generally assume uniform color and/or texture,1 and hence would perform very poorly on the complex, unconstrained, highly textured images that we consider.”
Deep Filter Banks for Texture Recognition, Description, and Segmentation (2015, background): “and Simoncelli 2000), and shape from texture (Gårding 1992; Forsyth 2001; Malik and Rosenholtz 1997).”
Single Image 3D without a Single 3D Image (2015, background): “Our style elements on the other hand, are discovered automatically via the regularity in large amounts of data, and are more general than instancelevel texture patterns.”
How Little Do We Need for 3-D Shape Perception? (2011, background): “Malik and Rosenholtz (1997) designed an algorithm that estimates the affine transforms between nearby image patches in order to estimate 3-”