Semantic Image Matting

04/16/2021
by   Yanan Sun, et al.
0

Natural image matting separates the foreground from background in fractional occupancy which can be caused by highly transparent objects, complex foreground (e.g., net or tree), and/or objects containing very fine details (e.g., hairs). Although conventional matting formulation can be applied to all of the above cases, no previous work has attempted to reason the underlying causes of matting due to various foreground semantics. We show how to obtain better alpha mattes by incorporating into our framework semantic classification of matting regions. Specifically, we consider and learn 20 classes of matting patterns, and propose to extend the conventional trimap to semantic trimap. The proposed semantic trimap can be obtained automatically through patch structure analysis within trimap regions. Meanwhile, we learn a multi-class discriminator to regularize the alpha prediction at semantic level, and content-sensitive weights to balance different regularization losses. Experiments on multiple benchmarks show that our method outperforms other methods and has achieved the most competitive state-of-the-art performance. Finally, we contribute a large-scale Semantic Image Matting Dataset with careful consideration of data balancing across different semantic classes.

READ FULL TEXT

page 1

page 3

page 6

page 7

page 8

research
08/05/2022

TransMatting: Enhancing Transparent Objects Matting with Transformers

Image matting refers to predicting the alpha values of unknown foregroun...
research
03/18/2022

Location-Free Camouflage Generation Network

Camouflage is a common visual phenomenon, which refers to hiding the for...
research
09/10/2019

Semantic Foreground Inpainting from Weak Supervision

Semantic scene understanding is an essential task for self-driving vehic...
research
07/16/2021

Rectifying the Shortcut Learning of Background: Shared Object Concentration for Few-Shot Image Recognition

Few-Shot image classification aims to utilize pretrained knowledge learn...
research
08/10/2019

Unconstrained Foreground Object Search

Many people search for foreground objects to use when editing images. Wh...
research
01/07/2021

Multi-scale Information Assembly for Image Matting

Image matting is a long-standing problem in computer graphics and vision...
research
10/30/2020

End-to-end Animal Image Matting

Extracting accurate foreground animals from natural animal images benefi...

Please sign up or login with your details

Forgot password? Click here to reset