DeepIcon: A Hierarchical Network for Layer-wise Icon Vectorization

TL;DR

DeepIcon is a hierarchical neural network that converts raster images into accurate, editable SVG icon vectors, overcoming previous limitations in shape completeness and semantic preservation.

Contribution

It introduces a novel hierarchical network architecture for variable-length icon vectorization directly from raster images, improving accuracy and semantic understanding.

Findings

Produces high-quality SVG icons from raster images

Outperforms existing methods in shape completeness and semantic accuracy

Operates efficiently without a differentiable rasterizer

Abstract

In contrast to the well-established technique of rasterization, vectorization of images poses a significant challenge in the field of computer graphics. Recent learning-based methods for converting raster images to vector formats frequently suffer from incomplete shapes, redundant path prediction, and a lack of accuracy in preserving the semantics of the original content. These shortcomings severely hinder the utility of these methods for further editing and manipulation of images. To address these challenges, we present DeepIcon, a novel hierarchical image vectorization network specifically tailored for generating variable-length icon vector graphics based on the raster image input. Our experimental results indicate that DeepIcon can efficiently produce Scalable Vector Graphics (SVGs) directly from raster images, bypassing the need for a differentiable rasterizer while also demonstrating a profound understanding of the image contents.