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

• URL: http://arxiv.org/abs/2603.24039v1
• Date: Wed, 25 Mar 2026 07:51:04 GMT
• Title: SemLayer: Semantic-aware Generative Segmentation and Layer Construction for Abstract Icons
• Abstract summary: SemLayer is a visual generation empowered pipeline that restores editable layered structures.<n>We formalize this problem as semantic layer construction for flattened vector art.<n>We demonstrate the effectiveness of SemLayer, enabling previously inapplicable to flattened vector graphics and establishing semantic layer reconstruction as a practical and valuable task.
• Score: 53.57408001182251
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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/

Related papers

• Workflow-Aware Structured Layer Decomposition for Illustration Production [9.48320994682878]
  We propose a workflow-aware structured layer decomposition framework tailored to the illustration production of anime artwork.<n>Inspired by the creation pipeline of anime production, our method decomposes the illustration into semantically meaningful production layers.<n> Experiments demonstrate that the accurate and visually coherent layer decompositions were achieved by using our method.
  arXiv  Detail & Related papers  (2026-03-16T07:28:37Z)
• LayerD: Decomposing Raster Graphic Designs into Layers [15.294433619347082]
  LayerD is a method to decompose graphic designs into layers for re-editable creative workflow.<n>We propose a simple yet effective refinement approach taking advantage of the assumption that layers often exhibit uniform appearance.<n>In experiments, we show that LayerD successfully achieves high-quality decomposition and outperforms baselines.
  arXiv  Detail & Related papers  (2025-09-29T17:50:12Z)
• LayerPeeler: Autoregressive Peeling for Layer-wise Image Vectorization [14.917583676464266]
  We introduce LayerPeeler, a novel layer-wise image vectorization approach.<n>By identifying and removing the topmost non-occluded layers, we generate vector graphics with complete paths and coherent layer structures.<n>Our method leverages vision-language models to construct a layer graph that captures relationships among elements.
  arXiv  Detail & Related papers  (2025-05-29T17:58:03Z)
• OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting [54.525583840585305]
  We introduce OmniPaint, a unified framework that re-conceptualizes object removal and insertion as interdependent processes.<n>Our novel CFD metric offers a robust, reference-free evaluation of context consistency and object hallucination.
  arXiv  Detail & Related papers  (2025-03-11T17:55:27Z)
• Generative Image Layer Decomposition with Visual Effects [49.75021036203426]
  LayerDecomp is a generative framework for image layer decomposition.<n>It produces clean backgrounds and high-quality transparent foregrounds with faithfully preserved visual effects.<n>Our method achieves superior quality in layer decomposition, outperforming existing approaches in object removal and spatial editing tasks.
  arXiv  Detail & Related papers  (2024-11-26T20:26:49Z)
• Structure-Guided Image Completion with Image-level and Object-level Semantic Discriminators [97.12135238534628]
  We propose a learning paradigm that consists of semantic discriminators and object-level discriminators for improving the generation of complex semantics and objects. Specifically, the semantic discriminators leverage pretrained visual features to improve the realism of the generated visual concepts. Our proposed scheme significantly improves the generation quality and achieves state-of-the-art results on various tasks.
  arXiv  Detail & Related papers  (2022-12-13T01:36:56Z)
• Towards Layer-wise Image Vectorization [57.26058135389497]
  We propose Layerwise Image Vectorization, namely LIVE, to convert images to SVGs and simultaneously maintain its image topology. Live generates compact forms with layer-wise structures that are semantically consistent with human perspective. Live initiates human editable SVGs for both designers and can be used in other applications.
  arXiv  Detail & Related papers  (2022-06-09T17:55:02Z)
• Anti-aliasing Semantic Reconstruction for Few-Shot Semantic Segmentation [66.85202434812942]
  We reformulate few-shot segmentation as a semantic reconstruction problem. We convert base class features into a series of basis vectors which span a class-level semantic space for novel class reconstruction. Our proposed approach, referred to as anti-aliasing semantic reconstruction (ASR), provides a systematic yet interpretable solution for few-shot learning problems.
  arXiv  Detail & Related papers  (2021-06-01T02:17:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.