What question did this study set out to answer?

This research aims to improve the estimation of alpha in natural images where object boundaries are complex.

synapse

⌘+K

synapse

⌘+K

November 7, 2002

Alpha estimation in natural images

Key Points

This research aims to improve the estimation of alpha in natural images where object boundaries are complex.
Proposed a new technique extending blue screen matting for various color distributions.
Required coarse knowledge of boundary locations for effective application.
Implemented object transfer from one image to another while preserving naturalism.
Successfully moved different natural objects between images while maintaining visual coherence.
Demonstrated improved accuracy in alpha estimation for complex boundaries involving multiple colors.

Abstract

Many boundaries between objects in the world project onto curves in an image. However, boundaries involving natural objects (e.g., trees, hair, water, smoke) are often unworkable under this model because many pixels receive light from more than one object. We propose a technique for estimating alpha, the proportion in which two colors mix to produce a color at the boundary. The technique extends blue screen matting to backgrounds that have almost arbitrary color distributions, though coarse knowledge of the boundary's location is required. Results show a number of different objects moved from one image to another while maintaining naturalism.

Mark Helpful

Bookmark

Relay