Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/166590
Title: Portrait matting using an attention-based memory network
Authors: Song, Shufeng
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2023
Publisher: Nanyang Technological University
Source: Song, S. (2023). Portrait matting using an attention-based memory network. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/166590
Abstract: Matting is the process of generating prediction alpha and foreground with rich details from the input images. There are three major challenges for traditional matting algorithms. Firstly, most of them focus on auxiliary-based matting, while putting those algorithms into daily use is impractical since additional input is not applicable in most scenarios. The second thing is the construction of temporal-guided modules to exploit temporal coherence for video matting tasks. Last but not least is the availability of matting datasets. This thesis addresses the above challenges and proposes a novel auxiliary-free video matting network. To eliminate the reliance on additional inputs, we perform a interleaved training strategy, in which we use binary masks from segmentation outputs to help our model to locate the portrait position and separate its boundary from the background. Then, we design a temporal-guided memory module based on the attention mechanism to compute and store the temporal coherence among video frames. Moreover, we also provide direct supervision for the the attention-based memory block to further boost the network’s robustness. Finally, we collect multiple matting datasets to generate synthesized video clips for training and testing. The validation results show that our method outperforms several state-of-the-art methods in terms of the alpha and foreground prediction quality and temporal consistency.
URI: https://hdl.handle.net/10356/166590
DOI: 10.32657/10356/166590
Schools: School of Electrical and Electronic Engineering 
Rights: This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License (CC BY-NC 4.0).
Fulltext Permission: embargo_20240427
Fulltext Availability: With Fulltext
Appears in Collections:EEE Theses

Files in This Item:
File Description SizeFormat 
Thesis_Amended_version_final.pdf
  Until 2024-04-27
5.31 MBAdobe PDFUnder embargo until Apr 27, 2024

Page view(s)

150
Updated on Apr 14, 2024

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.