LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization

TL;DR

LayerPeeler introduces an autoregressive layer peeling method for image vectorization that effectively handles occlusions, producing complete, coherent vector graphics by leveraging vision-language models and diffusion-based editing.

Contribution

The paper presents a novel layer-wise vectorization approach using autoregressive peeling and vision-language models, improving quality and flexibility over existing methods.

Findings

Outperforms existing vectorization techniques in quality and coherence.

Generates vector graphics with complete paths and clear layer structures.

Achieves superior geometric regularity and visual fidelity.

Abstract

Image vectorization is a powerful technique that converts raster images into vector graphics, enabling enhanced flexibility and interactivity. However, popular image vectorization tools struggle with occluded regions, producing incomplete or fragmented shapes that hinder editability. While recent advancements have explored optimization-based and learning-based layer-wise image vectorization, these methods face limitations in vectorization quality and flexibility. In this paper, we introduce LayerPeeler, a novel layer-wise image vectorization approach that addresses these challenges through a progressive simplification paradigm. The key to LayerPeeler's success lies in its autoregressive peeling strategy: by identifying and removing the topmost non-occluded layers while recovering underlying content, we generate vector graphics with complete paths and coherent layer structures. Our method leverages vision-language models to construct a layer graph that captures occlusion relationships among elements, enabling precise detection and description for non-occluded layers. These descriptive captions are used as editing instructions for a finetuned image diffusion model to remove the identified layers. To ensure accurate removal, we employ localized attention control that precisely guides the model to target regions while faithfully preserving the surrounding content. To support this, we contribute a large-scale dataset specifically designed for layer peeling tasks. Extensive quantitative and qualitative experiments demonstrate that LayerPeeler significantly outperforms existing techniques, producing vectorization results with superior path semantics, geometric regularity, and visual fidelity.