Corpus ID: 211075899

Background Matting

@article{Javidnia2020BackgroundM,
  title={Background Matting},
  author={Hossein Javidnia and Franccois Piti'e},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.04433}
}
The current state of the art alpha matting methods mainly rely on the trimap as the secondary and only guidance to estimate alpha. This paper investigates the effects of utilising the background information as well as trimap in the process of alpha calculation. To achieve this goal, a state of the art method, AlphaGan is adopted and modified to process the background information as an extra input channel. Extensive experiments are performed to analyse the effect of the background information in… Expand

Figures, Tables, and Topics from this paper

An Advert Creation System for 3D Product Placements
TLDR
A Video Advertisement Placement & Integration (Adverts) framework, which is capable of perceiving the 3D geometry of the scene and camera motion to blend 3D virtual objects in videos and create the illusion of reality is presented. Expand
Alpha Matte Generation from Single Input for Portrait Matting
TLDR
An additional input-free approach to perform portrait matting using Generative Adversarial Nets (GANs), which outperformed the MODNet method that also takes a single input and obtained comparable results with BGM-V2 and FBA methods that require additional input. Expand

References

SHOWING 1-10 OF 50 REFERENCES
A Late Fusion CNN for Digital Matting
TLDR
Experimental results demonstrate that the structure of a deep convolutional neural network to predict the foreground alpha matte by taking a single RGB image as input can achieve high-quality alpha mattes for various types of objects and outperform the state-of-the-art CNN-based image matting methods on the human imageMatting task. Expand
Shared Sampling for Real‐Time Alpha Matting
TLDR
The first real‐time alpha matting technique for natural images and videos is presented, based on the observation that, for small neighborhoods, pixels tend to share similar attributes, and achieves speedups of up to two orders of magnitude compared to previous ones, while producing high‐quality alpha mattes. Expand
Nonlocal matting
TLDR
The key observation is that the nonlocal principle, introduced to denoise images, can be successfully applied to the alpha matte to obtain sparsity in matte representation, and therefore dramatically reduce the number of pixels a user needs to manually label. Expand
Very Deep Residual Network for Image Matting
TLDR
Experimental results show the proposed deep learning based matting algorithm can tackle complicated foreground textures even it has similar color with background, and demonstrates the method outperforms previous methods, especially in tackling fine structure. Expand
Disentangled Image Matting
TLDR
This paper proposes AdaMatting, a new end-to-end matting framework that disentangles this problem into two sub-tasks: trimap adaptation and alpha estimation, which achieves the state-of-the-art performance on Adobe Composition-1k dataset both qualitatively and quantitatively. Expand
Perceptually Motivated Benchmark for Video Matting
TLDR
An online benchmark for video-matting methods is presented to enable better understanding of current progress in the field of video matting and to aid in developing new methods. Expand
KNN Matting
TLDR
The matting technique, aptly called KNN matting, capitalizes on the nonlocal principle by using K nearest neighbors (KNN) in matching nonlocal neighborhoods, and contributes a simple and fast algorithm giving competitive results with sparse user markups. Expand
A global sampling method for alpha matting
TLDR
This paper proposes a global sampling method that uses all samples available in the image to handle the computational complexity introduced by the large number of samples, and poses the sampling task as a correspondence problem. Expand
Learning-Based Sampling for Natural Image Matting
TLDR
The estimation of the layer colors through the use of deep neural networks prior to the opacity estimation is a better match for the capabilities of neural networks, and the availability of these colors substantially increase the performance of opacity estimation due to the reduced number of unknowns in the compositing equation. Expand
Image and Video Matting: A Survey
TLDR
This survey provides a comprehensive review of existing image and video matting algorithms and systems, with an emphasis on the advanced techniques that have been recently proposed. Expand
...
1
2
3
4
5
...