Differentiable vector graphics rasterization for editing and learning

Abstract

We introduce a differentiable rasterizer that bridges the vector graphics and raster image domains, enabling powerful raster-based loss functions, optimization procedures, and machine learning techniques to edit and generate vector content. We observe that vector graphics rasterization is differentiable after pixel prefiltering. Our differentiable rasterizer offers two prefiltering options: an analytical prefiltering technique and a multisampling anti-aliasing technique. The analytical variant is faster but can suffer from artifacts such as conflation. The multisampling variant is still efficient, and can render high-quality images while computing unbiased gradients for each pixel with respect to curve parameters.

Document Details

Document Type
Pub Defense Publication
Publication Date
Nov 27, 2020
Source ID
10.1145/3414685.3417871

Entities

People

  • Jonathan Ragan-Kelley
  • Michael Gharbi
  • Michal Lukáč
  • Tzu-mao Li

Organizations

  • Adobe
  • Defense Advanced Research Projects Agency
  • Massachusetts Institute of Technology

Tags

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Image Processing and Computer Vision.
  • Operations Research

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks