Determining Three-Dimensional Shape from Orientation and Spatial Frequency Disparities

How researchers see this paper

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

Hypercolumns for object segmentation and fine-grained localization (2014, neutral): “This representation also proved useful for optical flow [39] and stereo [26].”
Cross Modal Distillation for Supervision Transfer (2015, background): “ervision transfer carry useful information. [30] hypothesize that information from intermediate layers in such hierarchies carry information which may be useful for ﬁne grained tasks. Jones and Malik [29] and Weber and Malik [51] and in more recent work Hariharan et al. [20] and Long et al. [36] ope”
Robust computation of optical flow in a multi-scale differential framework (1993, methodology): “The convolution with a series of filters is a common starting point for a number of early vision tasks such as edge detection, stereopsis and texture discrimination (Bergen and Adelson 1988; Canny 1986; Jones and Malik 1992; Jones and Malik t992; Malik and Perona 1990; Turner 1986 and Heeger 1988).”
Computing Local Surface Orientation and Shape from Texture for Curved Surfaces (1997, background): “We wish to find the matrix, A, which represents the affine transformation between the spherically projected P1: STR/JHR P2: STR/PMR/ASH P3: PMR/ASH QC: PMR/BSA T1: PMR International Journal of Computer Vision KL444-03-Malik May 12, 1997 13:31 154 Malik and Rosenholtz Figure 2 .”