Multi-view Stereo Beyond Lambert

Multi-view Stereo Beyond Lambert (2002)

Cached

Download Links

Other Repositories/Bibliography

CiteULike
DBLP

by Hailin Jin , Stefano Soatto , Anthony J. Yezzi

Venue:	In International Conference on Computer Vision and Pattern Recognition
Citations:	44 - 7 self

Versions

Version History

Metadata Version 3

User correction supplied by SystemCorrections

Datum	Value	Source
TITLE	Multi-view Stereo Beyond Lambert	user correction - Legacy Corrections
AUTHOR NAME	Hailin Jin	user correction - Legacy Corrections
AUTHOR AFFIL	y	user correction - Legacy Corrections
AUTHOR NAME	Stefano Soatto	user correction - Legacy Corrections
AUTHOR AFFIL	x	user correction - Legacy Corrections
AUTHOR NAME	Anthony J. Yezzi	user correction - Legacy Corrections
AUTHOR AFFIL	; z; y Electrical Engineering Department, Washington University, St. Louis- MO 63130, hljin@ee.wustl.edu; z Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta- GA 30332	user correction - Legacy Corrections
AUTHOR ADDR	; x Computer Science Department, University of California, Los Angeles- CA 90095,; ayezzi@ece.gatech.edu	user correction - Legacy Corrections
ABSTRACT	We consider the problem of estimating the shape and radiance of an object from a calibrated set of views under the assumption that the reflectance of the object is nonLambertian. Unlike traditional stereo, we do not solve the correspondence problem by comparing image-to-image. Instead, we exploit a rank constraint on the radiance tensor field of the surface in space, and use it to define a discrepancy measure between each image and the underlying model. Our approach automatically returns an estimate of the radiance of the scene, along with its shape, represented by a dense surface. The former can be used to generate novel views that capture the non-Lambertian appearance of the scene.	user correction - Legacy Corrections
YEAR	2002	user correction - Legacy Corrections
VENUE	In International Conference on Computer Vision and Pattern Recognition	INFERENCE
VENUE TYPE	CONFERENCE	INFERENCE
PAGES	171--178	INFERENCE
VOLUME	1	INFERENCE
CITATIONS	19 found	ParsCit 1.0