Name
Abstract | ||
|---|---|---|
Traditional sketch segmentation methods mainly rely on handcrafted features and complicate models, and their performance is far from satisfactory due to the abstract representation of sketches. Recent success of Deep Neural Networks (DNNs) in related tasks suggests DNNs could be a practical solution for this problem, yet the suitable datasets for learning and evaluating DNNs are limited. To this end, we introduce SketchSeg, a large dataset consisting of 10,000 pixel-wisely labeled sketches. Besides, due to the lack of colors and textures in sketches, conventional DNNs learned on natural images are not optimal for tackling our problem. Therefore, we further propose the Multi-column Point-CNN (MCPNet), which directly takes sampled points as its input to reduce computational costs, and adopts multiple columns with different filter sizes to better capture the structures of sketches. Extensive experiments validate that the MCPNet is superior to conventional DNNs like FCN. The SketchSeg dataset is publicly available on https://drive.google.com/open?id=1OpCBvkInhxvfAHuVs-spDEppb8iXFC3C. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.neucom.2019.12.117 | Neurocomputing |
Keywords | DocType | Volume |
Sketch segmentation,MCPNet,Deep neural network | Journal | 392 |
ISSN | Citations | PageRank |
0925-2312 | 0 | 0.34 |
References | Authors | |
18 | 7 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Fei Wang | 1 | 5 | 1.50 |
| Shujin Lin | 2 | 77 | 7.74 |
| Hanhui Li | 3 | 0 | 0.34 |
| Hefeng Wu | 4 | 90 | 14.67 |
| Tie Cai | 5 | 0 | 2.03 |
| Xiaonan Luo | 6 | 697 | 92.76 |
| Ruomei Wang | 7 | 35 | 20.82 |