Alpha estimation in natural images

Citations Over TimeTop 1% of 2002 papers

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.

Related Papers

• → Point-pixel fusion for object detection and depth estimation(2022)1 cited
• → Dynamic Targets Detection for Robotic Applications Using Panoramic Vision System(2007)1 cited
• → Towards Object Detection from Motion(2019)1 cited
• → Object extraction from stereo vision using continuity of disparity map(2012)
• Foreground and shadow detection for video surveillance(2009)