SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons

2026-03-25

AI Summary

Flat abstract icons lack semantic layer information, making them unsuitable for downstream tasks such as editing, redrawing, and animation. This work formalizes semantic layer reconstruction as a generative segmentation and completion problem and proposes an end-to-end pipeline that integrates generative vision models, semantic segmentation, geometric completion, and vector composition to recover layered vector structures with occlusion relationships from a single flat icon. The method not only achieves semantic completion of occluded regions and decouples color from structure but also reconstructs editable semantic layers. Experiments demonstrate that the proposed approach significantly enhances the editability and reusability of icon structures, outperforming existing methods on both qualitative and quantitative metrics.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Deep Generative Models & Autoencoders
• Natural Language Processing: Generation

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications

Abstract

Graphic icons are a cornerstone of modern design workflows, yet they are often distributed as flattened single-path or compound-path graphics, where the original semantic layering is lost. This absence of semantic decomposition hinders downstream tasks such as editing, restyling, and animation. We formalize this problem as semantic layer construction for flattened vector art and introduce SemLayer, a visual generation empowered pipeline that restores editable layered structures. Given an abstract icon, SemLayer first generates a chromatically differentiated representation in which distinct semantic components become visually separable. To recover the complete geometry of each part, including occluded regions, we then perform a semantic completion step that reconstructs coherent object-level shapes. Finally, the recovered parts are assembled into a layered vector representation with inferred occlusion relationships. Extensive qualitative comparisons and quantitative evaluations demonstrate the effectiveness of SemLayer, enabling editing workflows previously inapplicable to flattened vector graphics and establishing semantic layer reconstruction as a practical and valuable task. Project page: https://xxuhaiyang.github.io/SemLayer/

Problem

• semantic layer construction
• flattened vector graphics
• abstract icons
• semantic decomposition
• layered representation

Innovation

• semantic layer construction
• generative segmentation
• vector graphics editing
• occlusion-aware reconstruction
• abstract icon decomposition