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

2026-03-25 · Haiyang Xu, Ronghuan Wu, Li-Yi Wei, Nanxuan Zhao, Chenxi Liu, Cuong Nguyen, Zhuowen Tu, Zhaowen Wang arxiv

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/

📄 PDF Abstract BibTeX arXiv:2603.24039

Code (0)

등록된 구현이 없습니다.

Learning Semantics-aware Distance Map with Semantics Layering Network for Amodal Instance Segmentation

2019-05-30 · Ziheng Zhang, Anpei Chen, Ling Xie, Jingyi Yu 외

In this work, we demonstrate yet another approach to tackle the amodal segmentation problem. Specifically, we first introduce a new representation, namely a semantics-aware distance map (sem-dist map), to serve as our ta…

Amodal Instance Segmentation Instance Segmentation Segmentation Semantic Segmentation

Learning High-level Prior with Convolutional Neural Networks for Semantic Segmentation

2015-11-22 · Haitian Zheng, Yebin Liu, Mengqi Ji, Feng Wu 외

This paper proposes a convolutional neural network that can fuse high-level prior for semantic image segmentation. Motivated by humans' vision recognition system, our key design is a three-layer generative structure cons…

Decoder Image Segmentation Segmentation Semantic Segmentation+1

DatasetNeRF: Efficient 3D-aware Data Factory with Generative Radiance Fields

2023-11-18 · Yu Chi, Fangneng Zhan, Sibo Wu, Christian Theobalt 외

Progress in 3D computer vision tasks demands a huge amount of data, yet annotating multi-view images with 3D-consistent annotations, or point clouds with part segmentation is both time-consuming and challenging. This pap…

Decoder Point Cloud Segmentation Segmentation Video Segmentation+1

Making Training-Free Diffusion Segmentors Scale with the Generative Power

2026-03-06 · Benyuan Meng, Qianqian Xu, Zitai Wang, Xiaochun Cao 외 arxiv

As powerful generative models, text-to-image diffusion models have recently been explored for discriminative tasks. A line of research focuses on adapting a pre-trained diffusion model to semantic segmentation without an…

Semantic Segmentation

Motion-Compensated Latent Semantic Canvases for Visual Situational Awareness on Edge

2025-12-29 · Igor Lodin, Sergii Filatov, Vira Filatova, Dmytro Filatov arxiv

We propose Motion-Compensated Latent Semantic Canvases (MCLSC) for visual situational awareness on resource-constrained edge devices. The core idea is to maintain persistent semantic metadata in two latent canvases - a s…

Panoptic Segmentation