Visual Reconstruction

Free Download

Authors:

Series: The MIT Press series in artificial intelligence

ISBN: 9780262022712, 0-262-02271-0

Size: 38 MB (39887731 bytes)

Pages: 232/232

File format:

Language:

Publishing Year:

Category: Tags: , ,

Andrew Blake, Andrew Zisserman9780262022712, 0-262-02271-0

Visual Reconstruction presents a unified and highly original approach to the treatment of continuity in vision. It introduces, analyzes, and illustrates two new concepts. The first – the weak continuity constraint – is a concise, computational formalization of piecewise continuity. It is a mechanism for expressing the expectation that visual quantities such as intensity, surface color, and surface depth vary continuously almost everywhere, but with occasional abrupt changes. The second concept – the graduated nonconvexity algorithm – arises naturally from the first. It is an efficient, deterministic (nonrandom) algorithm for fitting piecewise continuous functions to visual data.

Reviews

There are no reviews yet.

Be the first to review “Visual Reconstruction”
Shopping Cart
Scroll to Top