Scene-Level Sketches for Semantic Segmentation

This publication contains three new datasets for scene-level sketch semantic segmentation task, namely SKY-Scene, TUB-Scene, and Freehand-Scene. SKY-Scene and TUB-Scene are synthetic datasets, where the scene layout templates were extracted from dataset SketchyScene, and the object components were adopted from dataset Sketchy. They are composed to include more sketch-specific characteristics, e.g., sparsity, abstractness, and diversity, to truly evaluate segmentation performance. Freehand-Scene are fifty real human-drawn scene sketches for practical test.

本研究发布了三个面向场景级草图语义分割任务的新数据集，分别为SKY-Scene、TUB-Scene和Freehand-Scene。SKY-Scene和TUB-Scene为合成数据集，其场景布局模板源自SketchyScene数据集，物体组件则取自Sketchy数据集。这两个数据集的构建旨在涵盖更多草图特有的特征（如稀疏性、抽象性和多样性），以真实评估分割性能。Freehand-Scene包含五十幅真实人类绘制的场景草图，用于实际测试。