Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Sketch2Seq: Reconstruct CAD Models From Feature-Based Sketch Segmentation.

Yue Sun, Jituo Li, Ziqin Xu

    IEEE Transactions on Visualization and Computer Graphics
    |May 2, 2025
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    PGK1 Drives Glial Glycolytic Reprogramming to Mediate Isoflurane-Induced Cognitive Impairment in Aged Mice.

    Journal of cellular and molecular medicine·2026
    Same author

    Effects of SPINK5 on the Biological Characteristics of Oral Squamous Cell Carcinoma Cells and the NOTCH Signaling Pathway.

    Journal of stomatology, oral and maxillofacial surgery·2026
    Same author

    Stress and permeability evolution characteristics of a long distance upper protected coal seam based on hydromechanical coupling and gas extraction technology.

    Scientific reports·2026
    Same author

    Utilizing Serum Fluorescence Spectra and Machine Learning Algorithms for Efficient Diagnosis of Sheep Brucellosis.

    Journal of biophotonics·2026
    Same author

    Soil function reshaping and crop yield driving mechanisms in saline-alkali soil under freezing saline water irrigation.

    Frontiers in plant science·2026
    Same author

    Cu-Catalyzed dynamic kinetic asymmetric allylation enabled enantioselective assembly of sterically congested triaryl tertiary alcohols.

    Nature communications·2026
    Same journal

    FGO-SLAM++: Real-time Geometry-Aware Gaussian SLAM with Continuous Opacity Field.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    Blue Noise Dithering for Reservoir-based Spatio-temporal Importance Resampling.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    ROS-GS: Relightable Outdoor Scenes With Gaussian Splatting.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    MesoSplats: Texture Synthesis with Gaussian Splatting.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    GLLA: A Unified Force-Directed Graph Layout Framework Supporting Local Adjustments.

    IEEE transactions on visualization and computer graphics·2026
    Same journal

    Multi-Perception Crowd: Learning to combine entity and implicit perception for diverse crowd simulation.

    IEEE transactions on visualization and computer graphics·2026
    See all related articles

    Sketch2Seq automatically generates complex, editable CAD models from sketches, enhancing design accessibility. This system understands user intent, enabling sophisticated modeling without extra annotations.

    Area of Science:

    • Computer-Aided Design (CAD)
    • Computational Geometry
    • Machine Learning

    Background:

    • Sketch-based modeling aims to simplify CAD by enabling model creation from user sketches.
    • Existing methods often produce non-editable or limited editable models, hindering practical application.
    • Bridging the gap for novice users and non-professionals requires more robust and editable sketch-to-model solutions.

    Purpose of the Study:

    • To introduce Sketch2Seq, a novel system for generating complex, semantic, and editable CAD models directly from sketches.
    • To improve the understanding of user design intent within CAD sketches.
    • To facilitate the creation of editable CAD models without requiring additional user annotations.

    Main Methods:

    • Development of a novel sketch segmentation network utilizing geometric and topological features to identify operation features.

    Related Experiment Videos

  • Introduction of a new dataset specifically for CAD sketch segmentation.
  • Progressive generation and execution of CAD sequences, optimized for order and parameters using context models and input sketches.

    • Main Results:

    • The proposed sketch segmentation network effectively identifies diverse features in CAD sketches.
    • The Sketch2Seq system successfully generates complex and editable CAD models.
    • Experimental evaluations demonstrate the system's feasibility, superiority, and ability to handle longer sequences compared to existing methods.

    Conclusions:

    • Sketch2Seq offers a significant advancement in sketch-based modeling, producing high-quality, editable CAD models.
    • The system's ability to interpret design intent and generate editable outputs lowers the barrier for CAD software adoption.
    • This approach holds promise for expanding CAD usage among a wider audience, including designers and hobbyists.