L1-regularized Reconstruction Error as Alpha Matte

02/09/2017
by   Jubin Johnson, et al.
0

Sampling-based alpha matting methods have traditionally followed the compositing equation to estimate the alpha value at a pixel from a pair of foreground (F) and background (B) samples. The (F,B) pair that produces the least reconstruction error is selected, followed by alpha estimation. The significance of that residual error has been left unexamined. In this letter, we propose a video matting algorithm that uses L1-regularized reconstruction error of F and B samples as a measure of the alpha matte. A multi-frame non-local means framework using coherency sensitive hashing is utilized to ensure temporal coherency in the video mattes. Qualitative and quantitative evaluations on a dataset exclusively for video matting demonstrate the effectiveness of the proposed matting algorithm.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/11/2016

Sparse Coding for Alpha Matting

Existing color sampling based alpha matting methods use the compositing ...
research
02/11/2022

Signal reconstruction from noisy multichannel samples

We consider the signal reconstruction problem under the case of the sign...
research
01/24/2011

Reproducing Kernel Banach Spaces with the l1 Norm II: Error Analysis for Regularized Least Square Regression

A typical approach in estimating the learning rate of a regularized lear...
research
02/02/2016

Head Pose Estimation of Occluded Faces using Regularized Regression

This paper presents regression methods for estimation of head pose from ...
research
07/22/2018

A Trace Lasso Regularized L1-norm Graph Cut for Highly Correlated Noisy Hyperspectral Image

This work proposes an adaptive trace lasso regularized L1-norm based gra...
research
11/24/2021

Layered Controllable Video Generation

We introduce layered controllable video generation, where we, without an...
research
08/21/2021

Mixed Reality using Illumination-aware Gradient Mixing in Surgical Telepresence: Enhanced Multi-layer Visualization

Background and aim: Surgical telepresence using augmented perception has...

Please sign up or login with your details

Forgot password? Click here to reset