Image Vectorization with Real-Time Thin-Plate Spline
  Kuo-Wei Chen     Ying-Sheng Luo     Yu-Chi Lai     Yen-Lin Chen     Chih-Yuan Yao     Hong-Kuo Chu     Tong-Yee Lee  
Chen, K.-W., Luo, Y.-S., Lai, Y.-C., Chen, Y.-L., Yao, C.-Y., Chu, H.-K., and Lee, T.-Y., "Image Vectorization with Real-Time Thin-Plate Spline", IEEE Transaction on Multimedia, Volume XXX, Issue XXX, PP XXXX - XXXX, 2019, DOI:. Submitted web.
Abstract

The vector graphics with gradient mesh can be attributed to their compactness and scalability, however they tend to fall short when it comes to real-time editing due to lack of real time rasterization and efficient editing tool for image details. In this work, we encode global manipulation geometries and local image details within a hybrid vector structure using parametric patches and detailed features for localized and parallelized thin-plate spline(TPS) interpolation in order to achieve good compressibility, interactive expressibility, and editability. The proposed system then automatically extracts an optimal set of detailed color features while considering the compression ratio of the image as well as reconstruction error and its characteristics applicable to the preservation of structural and irregular saliency of image. The proposed real-time vector representation makes it possible to construct an interactive editing system for detail-maintained image magnification and color editing as well as material replacement in cross mapping, without maintaining spatial and temporal consistency while editing in a raster space. Experiments demonstrate that our representation method is superior to several state-of-the-art methods and as good as JPEG, while providing real-time editability and preserving structural and irregular saliency information.

Bibtex

@ARTICLE{Chen2019, 
author={Chen, K.-W. and Luo, Y.-S. and Lai, Y.-C. and Chen, Y.-L. and Yao, C.-Y. and Chu, H.-K. and Lee, T.-Y.}, 
journal={IEEE Transaction on Multimedia}, 
title={Image Vectorization with Real-Time Thin-Plate Spline}, 
year={2019}, 
volume={XXX}, 
number={XXX}, 
pages={XXXX-XXXX}, 
}

Acknowledgement

This work was supported by the National Science Council of Taiwan under Grants MOST107-2221-E-011-111, MOST107-2221-E-011-112-MY2, MOST107-2221-E-011-114-MY2, MOST107-2218-E-011-015, MOST106-2218-E-011-016, MOST106-3114-E-011-005, MOST105-2218-E-011-005, and MOST104-2221-E-011-029-MY3.

PDF