Publication Type
Journal Article
Version
acceptedVersion
Publication Date
11-2025
Abstract
In free-hand sketch recognition, state-of-the-art methods often struggle to extract spatial features from sketches with sparse distributions, which are characterized by significant blank regions devoid of informative content. To address this challenge, we introduce a novel framework for sketch recognition, termed Sketch-SparseNet. This framework incorporates an advanced convolutional component: the Sketch-Driven Dilated Deformable Block (SD3B). This component excels at extracting spatial features and accurately recognizing free-hand sketches with sparse distributions. The SD3B component innovatively bridges gaps in the blank areas of sketches by establishing spatial relationships among disconnected stroke points through adaptive reshaping of convolution kernels. These kernels are deformable, dilatable, and dynamically positioned relative to the sketch strokes, ensuring the preservation of spatial information from sketch points. Consequently, Sketch-SparseNet extracts a more accurate and compact representation of spatial features, enhancing sketch recognition performance. Additionally, we introduce the SmoothAlign loss function, which minimizes the disparity between the output features of parallel SD3B and CNNs, facilitating effective feature fusion. Extensive evaluations on the QuickDraw-414k and TU-Berlin datasets highlight our method’s state-of-the-art performance, achieving accuracies of 79.52% and 85.78%, respectively. To our knowledge, this work represents the first application of a sparse convolution framework that substantially alleviates the adverse effects of sparse sketch points. The codes are available at https://github.com/kingbackyang/Sketch-SparseNet.
Keywords
Sketch recognition, Sketch-SparseNet, Sketch-Driven Dilated Deformable Block, Point clouds, QuickDraw-414k, TU-Berlin
Discipline
Graphics and Human Computer Interfaces | Software Engineering
Research Areas
Software and Cyber-Physical Systems
Publication
Pattern Recognition
Volume
167
First Page
1
Last Page
12
ISSN
0031-3203
Identifier
10.1016/j.patcog.2025.111682
Publisher
Elsevier
Citation
YANG, Jingru; WANG, Jin; ZHOU, Yang; LU, Guodong; SUN, Yu; YU, Huan; FANG, Heming; LI, Zhihui; and Shengfeng HE.
Sketch-SparseNet: Sparse convolution framework for sketch recognition. (2025). Pattern Recognition. 167, 1-12.
Available at: https://ink.library.smu.edu.sg/sis_research/10479
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1016/j.patcog.2025.111682