English

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

Computer Vision and Pattern Recognition 2026-03-17 v2

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.

Keywords

Cite

@article{arxiv.2511.17454,
  title  = {Illustrator's Depth: Monocular Layer Index Prediction for Image Decomposition},
  author = {Nissim Maruani and Peiying Zhang and Siddhartha Chaudhuri and Matthew Fisher and Nanxuan Zhao and Vladimir G. Kim and Pierre Alliez and Mathieu Desbrun and Wang Yifan},
  journal= {arXiv preprint arXiv:2511.17454},
  year   = {2026}
}
R2 v1 2026-07-01T07:49:07.656Z