The existing high-quality environment matting methods usually require the capturing of a few thousand sample images and spend a few hours in data acquisition. In this paper, a novel environment matting algorithm is proposed to capture and extract the environment matte data effectively and efficiently. First, the recently developed compressive sensing theory is incorporated to reformulate the environment matting problem and simplify the data acquisition process. Next, taking into account the special properties of light refraction and reflection effects of transparent objects, two advanced priors, group clustering and Gaussian priors, as well as other basic constraints are introduced during the matte data recovery process to combat with the limited image samples, suppress the effects of the measurement noise resulted from data acquisition, and faithfully recover the sparse environment matte data. Compared with most of the existing environment matting methods, our algorithm significantly simplifies and accelerates the environment matting extraction process while still achieving high-accurate composition results.
- Modeling and recovery of physical attributes
- Picture/image generation