Prior-Induced Information Alignment for Image Matting

06/28/2021
by   Yuhao Liu, et al.
5

Image matting is an ill-posed problem that aims to estimate the opacity of foreground pixels in an image. However, most existing deep learning-based methods still suffer from the coarse-grained details. In general, these algorithms are incapable of felicitously distinguishing the degree of exploration between deterministic domains (certain FG and BG pixels) and undetermined domains (uncertain in-between pixels), or inevitably lose information in the continuous sampling process, leading to a sub-optimal result. In this paper, we propose a novel network named Prior-Induced Information Alignment Matting Network (PIIAMatting), which can efficiently model the distinction of pixel-wise response maps and the correlation of layer-wise feature maps. It mainly consists of a Dynamic Gaussian Modulation mechanism (DGM) and an Information Alignment strategy (IA). Specifically, the DGM can dynamically acquire a pixel-wise domain response map learned from the prior distribution. The response map can present the relationship between the opacity variation and the convergence process during training. On the other hand, the IA comprises an Information Match Module (IMM) and an Information Aggregation Module (IAM), jointly scheduled to match and aggregate the adjacent layer-wise features adaptively. Besides, we also develop a Multi-Scale Refinement (MSR) module to integrate multi-scale receptive field information at the refinement stage to recover the fluctuating appearance details. Extensive quantitative and qualitative evaluations demonstrate that the proposed PIIAMatting performs favourably against state-of-the-art image matting methods on the Alphamatting.com, Composition-1K and Distinctions-646 dataset.

READ FULL TEXT

page 1

page 2

page 3

page 6

page 7

page 9

page 10

research
12/12/2021

Pixel-wise Deep Image Stitching

Image stitching aims at stitching the images taken from different viewpo...
research
08/24/2021

Lossless Image Compression Using a Multi-Scale Progressive Statistical Model

Lossless image compression is an important technique for image storage a...
research
07/12/2022

Tracking Objects as Pixel-wise Distributions

Multi-object tracking (MOT) requires detecting and associating objects t...
research
05/26/2018

Enhanced-alignment Measure for Binary Foreground Map Evaluation

The existing binary foreground map (FM) measures to address various type...
research
05/19/2020

Associating Multi-Scale Receptive Fields for Fine-grained Recognition

Extracting and fusing part features have become the key of fined-grained...
research
10/26/2019

Region Mutual Information Loss for Semantic Segmentation

Semantic segmentation is a fundamental problem in computer vision. It is...
research
09/10/2019

Disentangled Image Matting

Most previous image matting methods require a roughly-specificed trimap ...

Please sign up or login with your details

Forgot password? Click here to reset