Paper Info
Title
Binocular Helmholtz Stereopsis
Abstract
Helmholtz stereopsis has been introduced recently as a surfacereconstruction technique that does not assume a modelof surface reflectance. In the reported formulation, correspondencewas established using a rank constraint, necessitatingat least three viewpoints and three pairs of images.Here, it is revealed that the fundamental Helmholtz stereopsisconstraint defines a nonlinear partial differential equation,which can be solved using only two images. It is shownthat, unlike conventional stereo, binocular Helmholtz stereopsisis able to establish correspondence (and thereby recoversurface depth) for objects having an arbitrary andunknown BRDF and in textureless regions (i.e., regions ofconstant or slowly varying BRDF). An implementation andexperimental results validate the method for specular surfaceswith and without texture.
Year
DOI
Venue
2003
10.1109/ICCV.2003.1238655
ICCV
Keywords
Field
DocType
fundamental helmholtz stereopsisconstraint,modelof surface reflectance,helmholtz stereopsis,recoversurface depth,regions ofconstant,arbitrary andunknown,nonlinear partial differential equation,implementation andexperimental result,binocular helmholtz stereopsis,rank constraint,conventional stereo,machine vision,stereo vision,bidirectional reflectance distribution function,partial differential equations,brdf,visual perception,image texture,visual system,computer vision,image reconstruction
Bidirectional reflectance distribution function,Helmholtz reciprocity,Iterative reconstruction,Surface reconstruction,Computer vision,Image texture,Stereopsis,Helmholtz free energy,Artificial intelligence,Partial differential equation,Mathematics
Conference
ISBN
Citations 
PageRank 
0-7695-1950-4
18
1.17
References 
Authors
16
5
Name
Order
Citations
PageRank
Todd Zickler1155571.72
Jeffrey Ho22190101.78
David Kriegman37693451.96
Jean Ponce412182902.31
Peter N. Belhumeur5122421001.27