Abstract
We present a simple and efficient method based on deep learning to automatically decompose sketched objects into semantically valid parts. We train a deep neural network to transfer existing segmentations and labelings from 3D models to freehand sketches without requiring numerous well-annotated sketches as training data. The network takes the binary image of a sketched object as input and produces a corresponding segmentation map with per-pixel labelings as output. A subsequent post-process procedure with multi-label graph cuts further refines the segmentation and labeling result. We validate our proposed method on two sketch datasets. Experiments show that our method outperforms the state-of-the-art method in terms of segmentation and labeling accuracy and is significantly faster, enabling further integration in interactive drawing systems. We demonstrate the efficiency of our method in a sketch-based modeling application that automatically transforms input sketches into 3D models by part assembly.
| Original language | English |
|---|---|
| Pages (from-to) | 38-51 |
| Number of pages | 14 |
| Journal | IEEE Computer Graphics and Applications |
| Volume | 39 |
| Issue number | 2 |
| Online published | 6 Dec 2018 |
| DOIs | |
| Publication status | Published - Mar 2019 |
Publisher's Copyright Statement
- COPYRIGHT TERMS OF DEPOSITED POSTPRINT FILE: © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
RGC Funding Information
- RGC-funded
Fingerprint
Dive into the research topics of 'Fast Sketch Segmentation and Labeling with Deep Learning'. Together they form a unique fingerprint.Projects
- 2 Finished
-
GRF: Data-driven Structure-adaptive Editing of Man-made Objects
FU, H. (Principal Investigator / Project Coordinator)
1/01/17 → 24/06/21
Project: Research
-
GRF: Data-Driven 3D Interpretation of Freehand Drawings
FU, H. (Principal Investigator / Project Coordinator)
1/11/14 → 1/04/19
Project: Research
Prizes
Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver