|
3D Shape Estimation & Image Restoration: Exploiting Defocus & Motion-Blur
Images contain information about the spatial properties of the scene they depict. When coupled with suitable assumptions, images can be used to infer three-dimensional information. This useful volume concentrates on motion blur and defocus, which can be exploited to infer the 3-D structure of a scene - as well as its radiance properties - and which
in turn can be used to generate novel images with better quality.
3-D Shape Estimation and Image Restoration presents a coherent framework for the analysis and design of algorithms to estimate 3-D shape from defocused and motion blurred images, and to eliminate defocus and motion blur to yield "restored" images. It provides a collection of algorithms that are optimal with respect to the chosen model and estimation criterion.
Visual Cues for Shape and Motion.- Basic Models of Image Formation.- When Can 3D Shape Be Reconstructed from Blurred Images?- A First Solution: Least-Squares.- Enforcing Positivity.- Defocus via Diffusion: Modeling and Reconstruction from Two Views.- Shape from the Defocus of Multiple Images.- Modeling Motion-Blur and Defocus via Diffusion.- Dealing with Occlusions.- Conclusions and Open Issues.- Appendixes: Concepts of Radiometry.- A PDE Primer.- Proofs of Propositions.- Calibration of Defocused Images.- Matlab Implementation of Some Algorithms.- Index.
|
