Summary: Accurate, Dense, and Robust Multi-View Stereopsis
Yasutaka Furukawa1
Department of Computer Science
and Beckman Institute
University of Illinois at Urbana-Champaign, USA1
Jean Ponce1,2
Willow Team­ENS/INRIA/ENPC
D´epartement d'Informatique
Ecole Normale Sup´erieure, Paris, France2
Abstract: This paper proposes a novel algorithm for calibrated
multi-view stereopsis that outputs a (quasi) dense set of rectan-
gular patches covering the surfaces visible in the input images.
This algorithm does not require any initialization in the form of a
bounding volume, and it detects and discards automatically out-
liers and obstacles. It does not perform any smoothing across
nearby features, yet is currently the top performer in terms of both
coverage and accuracy for four of the six benchmark datasets pre-
sented in [20]. The keys to its performance are effective tech-
niques for enforcing local photometric consistency and global
visibility constraints. Stereopsis is implemented as a match, ex-

Source: Anderson, Richard - Department of Computer Science and Engineering, University of Washington at Seattle
École Normale Supérieure, Laboratoire d'Informatique, WILLOW Computer vision and machine learning research laboratory

Collections: Computer Technologies and Information Sciences; Engineering