# Fast Sketch Segmentation and Labeling with Deep Learning

arXiv: https://arxiv.org/abs/1807.11847 · HTML: https://mlsanity.com/paper/1807.11847/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Jul 2018.

## Built on by (most cited first, 9 of 9)

- [FloorPlanCAD: A Large-Scale CAD Drawing Dataset for Panoptic Symbol Spotting](https://mlsanity.com/paper/2105.07147/) (2021)
- [One Sketch for All: One-Shot Personalized Sketch Segmentation](https://mlsanity.com/paper/2112.10838/) (2021)
- [Open Vocabulary Semantic Scene Sketch Understanding](https://mlsanity.com/paper/2312.12463/) (2023)
- [Sketch Beautification: Learning Part Beautification and Structure Refinement for Sketches of Man-made Objects](https://mlsanity.com/paper/2306.05832/) (2023)
- [Sketch Input Method Editor: A Comprehensive Dataset and Methodology for Systematic Input Recognition](https://mlsanity.com/paper/2311.18254/) (2023)
- [Class-Agnostic Visio-Temporal Scene Sketch Semantic Segmentation](https://mlsanity.com/paper/2410.00266/) (2024)
- [Extensions of Karger's Algorithm: Why They Fail in Theory and How They Are Useful in Practice](https://mlsanity.com/paper/2110.02750/) (2021)
- [DrawMon: A Distributed System for Detection of Atypical Sketch Content in Concurrent Pictionary Games](https://mlsanity.com/paper/2211.05429/) (2022)
- [Semantics-Preserving Sketch Embedding for Face Generation](https://mlsanity.com/paper/2211.13015/) (2022)

## Abstract (arXiv)

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.