Hierarchical Opacity Propagation for Image Matting

04/07/2020
by   Yaoyi Li, et al.
0

Natural image matting is a fundamental problem in computational photography and computer vision. Deep neural networks have seen the surge of successful methods in natural image matting in recent years. In contrast to traditional propagation-based matting methods, some top-tier deep image matting approaches tend to perform propagation in the neural network implicitly. A novel structure for more direct alpha matte propagation between pixels is in demand. To this end, this paper presents a hierarchical opacity propagation (HOP) matting method, where the opacity information is propagated in the neighborhood of each point at different semantic levels. The hierarchical structure is based on one global and multiple local propagation blocks. With the HOP structure, every feature point pair in high-resolution feature maps will be connected based on the appearance of input image. We further propose a scale-insensitive positional encoding tailored for image matting to deal with the unfixed size of input image and introduce the random interpolation augmentation into image matting. Extensive experiments and ablation study show that HOP matting is capable of outperforming state-of-the-art matting methods.

READ FULL TEXT

page 2

page 10

page 14

research
05/24/2021

Robust Watermarking using Diffusion of Logo into Autoencoder Feature Maps

Digital contents have grown dramatically in recent years, leading to inc...
research
07/06/2020

GCN for HIN via Implicit Utilization of Attention and Meta-paths

Heterogeneous information network (HIN) embedding, aiming to map the str...
research
12/22/2022

Restoring Vision in Hazy Weather with Hierarchical Contrastive Learning

Image restoration under hazy weather condition, which is called single i...
research
08/03/2018

Visual Reasoning with Multi-hop Feature Modulation

Recent breakthroughs in computer vision and natural language processing ...
research
09/20/2019

Context-Aware Image Matting for Simultaneous Foreground and Alpha Estimation

Natural image matting is an important problem in computer vision and gra...
research
07/24/2018

Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks

We study the problem of synthesizing a number of likely future frames fr...
research
11/24/2017

Visual Feature Attribution using Wasserstein GANs

Attributing the pixels of an input image to a certain category is an imp...

Please sign up or login with your details

Forgot password? Click here to reset