Illustrator's Depth: Monocular Layer Index Prediction for Image Decomposition

TL;DR

This paper introduces Illustrator's Depth, a new depth definition for decomposing images into editable layers, enabling advanced editing and generation applications through a neural network trained on layered vector graphics.

Contribution

It proposes a novel depth concept inspired by artistic processes and develops a neural network to predict layer indices from raster images, enhancing image decomposition and editing capabilities.

Findings

Outperforms state-of-the-art image vectorization methods

Enables high-fidelity text-to-vector graphics generation

Facilitates automatic 3D relief creation from 2D images

Abstract

We introduce Illustrator's Depth, a novel definition of depth that addresses a key challenge in digital content creation: decomposing flat images into editable, ordered layers. Inspired by an artist's compositional process, illustrator's depth infers a layer index to each pixel, forming an interpretable image decomposition through a discrete, globally consistent ordering of elements optimized for editability. We also propose and train a neural network using a curated dataset of layered vector graphics to predict layering directly from raster inputs. Our layer index inference unlocks a range of powerful downstream applications. In particular, it significantly outperforms state-of-the-art baselines for image vectorization while also enabling high-fidelity text-to-vector-graphics generation, automatic 3D relief generation from 2D images, and intuitive depth-aware editing. By reframing depth from a physical quantity to a creative abstraction, illustrator's depth prediction offers a new foundation for editable image decomposition.