Deep Learning for Free-Hand Sketch: A Survey

Abstract

Free-hand sketches are highly illustrative, and have been widely used by humans to depict objects or stories from ancient times to the present. The recent prevalence of touchscreen devices has made sketch creation a much easier task than ever and consequently made sketch-oriented applications increasingly popular. The progress of deep learning has immensely benefited free-hand sketch research and applications. This paper presents a comprehensive survey of the deep learning techniques oriented at free-hand sketch data, and the applications that they enable. The main contents of this survey include: (i) A discussion of the intrinsic traits and unique challenges of free-hand sketch, to highlight the essential differences between sketch data and other data modalities, e.g., natural photos. (ii) A review of the developments of free-hand sketch research in the deep learning era, by surveying existing datasets, research topics, and the state-of-the-art methods through a detailed taxonomy and experimental evaluation. (iii) Promotion of future work via a discussion of bottlenecks, open problems, and potential research directions for the community.

This paper is accepted by IEEE TPAMI

References in corpus (4)

• A Neural Representation of Sketch Drawings
• Sketch-based 3D Shape Retrieval using Convolutional Neural Networks
• Semi-Heterogeneous Three-Way Joint Embedding Network for Sketch-Based Image Retrieval
• SFSegNet: Parse Freehand Sketches using Deep Fully Convolutional Networks

Cited by in corpus (12)

• Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
• A Parallel Down-Up Fusion Network for Salient Object Detection in Optical Remote Sensing Images
• Multi-Graph Transformer for Free-Hand Sketch Recognition
• CoSE: Compositional Stroke Embeddings
• Deep Self-Supervised Representation Learning for Free-Hand Sketch
• Humans learn too: Better Human-AI Interaction using Optimized Human Inputs
• Engineering Sketch Generation for Computer-Aided Design
• C-DLinkNet: considering multi-level semantic features for human parsing
• Enabling Robots to Draw and Tell: Towards Visually Grounded Multimodal Description Generation
• Do Time Constraints Re-Prioritize Attention to Shapes During Visual Photo Inspection?
• Fine-Grained Instance-Level Sketch-Based Video Retrieval
• Mutltimodal AI Companion for Interactive Fairytale Co-creation