• Home
  • Search
  • CurveSDF: Binary Image Vectorization Using Signed Distance Fields
  • https://doi.org/10.1145/3591106.3592256Copy DOI Icon

CurveSDF: Binary Image Vectorization Using Signed Distance Fields

  • Jun 12, 2023
  • Zeqing Xia +1 more
Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Binary image vectorization is a classical and fundamental problem in the areas of Computer Graphics and Computer Vision. Existing image vectorization methods are mainly based on global optimization, typically failing to preserve important details on outlines due to the incapability of learning high-level knowledge from training data. To address this problem, we propose CurveSDF to facilitate the learning of vectorization for 2D outlines. Our method consists of the following three modules: convex separation, signed distance field (SDF) generation, and curve intersection calculation. Specifically, we first divide an input binary image into convex elements. Then, we use restrained curve-hyperplane divisions to generate their SDFs and precisely reconstruct the original image. Finally, we convert the generated SDFs to vector outlines composed of both Bezier curves and line segments. Moreover, our method is self-constrained, and thus there is no need to use any vector data for training. Experimental results demonstrate the effectiveness of our method and its superiority against other existing approaches for binary image vectorization.

Similar Papers
  • Research Article

Compilation of Different Approaches for Determining Illuminant Direction

  • Dec 31, 2019
  • The Frontiers of Society, Science and Technology
  • Tan Bowen +2
  • Research Article
  • Citations4

A hybrid-based texture synthesis approach

  • Mar 04, 2004
  • The Visual Computer
  • Wen-Kai Tai +2
  • PDF
  • Research Article
  • Citations12

Cross-Domain Correspondence for Sketch-Based 3D Model Retrieval Using Convolutional Neural Network and Manifold Ranking

  • Jan 01, 2020
  • IEEE Access
  • Shichao Jiao +5
  • Research Article

Practical Considerations to Skin Detection Scheme

  • Jan 01, 2006
  • The Journal of The Institute of Image Information and Television Engineers
  • Mohammad Ali Akbari +1
  • Book Chapter
  • Citations20

Anisotropic Range Image Integration

  • Jan 01, 2012
  • Christopher Schroers +5
  • PDF
  • Research Article
  • Citations3

Inferring implicit 3D representations from human figures on pictorial maps

  • Jul 28, 2023
  • Cartography and Geographic Information Science
  • Raimund Schnürer +4
  • Conference Article
  • Citations4

Joint Representation of Primitive and Non-primitive Objects for 3D Vision

  • Sep 01, 2018
  • Christiane Sommer +1
  • Research Article
  • Citations110

Image Stitching based on Feature Extraction Techniques: A Survey

  • Aug 20, 2014
  • International Journal of Computer Applications
  • Ebtsam Adel +2
  • Research Article
  • Citations370

Crowd Analysis Using Computer Vision Techniques

  • Sep 01, 2010
  • IEEE Signal Processing Magazine
  • Julio Silveira Jacques Junior +2
  • Conference Article
  • Citations17

Real time image mosaicing system based on feature extraction techniques

  • Dec 01, 2014
  • Ebtsam Adel +2
  • Conference Article
  • Citations1

Content-based authentication algorithm for binary images

  • Nov 01, 2009
  • Xinzhi Yao +3
  • Book Chapter
  • Citations16

Orthogonal Zig-Zag: An Efficient Method for Extracting Straight Lines from Engineering Drawings

  • Jan 01, 1992
  • Ian Chai +1
  • Conference Article
  • Citations2

Collision detection and response approaches for computer muscle modelling

  • Nov 23, 2022
  • Ondrej Havlicek +2
  • Research Article
  • Citations4

An Algorithm for Calculating Objects’ Shape Features in Binary Images

  • Oct 31, 2017
  • DEStech Transactions on Computer Science and Engineering
  • Lifeng He +5
  • Research Article
  • Citations413

3D distance fields: a survey of techniques and applications

  • Jul 01, 2006
  • IEEE Transactions on Visualization and Computer Graphics
  • M.W Jones +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.