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 Video

Updated: May 16, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Integrating SAM Supervision for 3D Weakly Supervised Point Cloud Segmentation.

Lechun You, Zhonghua Wu, Weide Liu

    IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society
    |May 14, 2026
    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

    For Intermediate-Size Sessile Serrated Lesions, Durable Clearance Should Remain the Decisive Endpoint.

    United European gastroenterology journal·2026
    Same author

    Therapeutic potential of wogonoside in hypertension-induced cardiac injury: Targeting apoptosis and MAPK signaling pathway.

    The Journal of nutritional biochemistry·2026
    Same author

    Polyethylene Terephthalate Microplastics Exposure Enhances the Risk of Ulcerative Colitis: Insights From Multi-Omics Integration, Machine Learning, and Molecular Docking Reveal Intestinal Toxicity Mechanisms: A Commentary.

    International journal of surgery (London, England)·2026
    Same author

    Exploring the toxicological network in diabetic microvascular disease: a commentary.

    International journal of surgery (London, England)·2026
    Same author

    Panax notoginseng saponin mitigates glycolysis to regulate macrophage polarization and sphingolipid metabolism via hypoxia-inducible factor-1 to alleviate atherosclerosis.

    Phytomedicine : international journal of phytotherapy and phytopharmacology·2025
    Same author

    Tetramethylpyrazine ameliorates 5-fluorouracil-Induced cardiotoxicity by inhibiting PANoptosis and suppressing the p38 MAPK/JNK/ERK signaling pathway.

    European journal of pharmacology·2025
    Same journal

    Change-Prior-Guided Unsupervised Change Detection of Heterogeneous Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    AgonicDreamer: Enhancing Multi-View Consistency in Text-to-3D Generation via Rectified Score Distillation.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    BiCM-Prompt: Bidirectional Cross-Modal Prompt Tuning for Class-Incremental Learning on Multisource Remote Sensing Images.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    GoP-based Quality Enhancement on Video Compression.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Align then Tensorize: Multi-Level Consistent Anchor Graph Learning for Scalable Multi-View Clustering.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same journal

    Beyond Fidelity: Diverse Image Synthesis via Retrieval-Augmented Diffusion.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    See all related articles

    This study introduces a novel method for 3D semantic segmentation using limited 3D data by leveraging 2D foundation models. The approach enhances 3D annotations with 2D segmentation masks, improving model performance.

    Area of Science:

    • Computer Vision
    • Machine Learning
    • 3D Data Analysis

    Background:

    • Annotating 3D point cloud data is challenging due to its size and complexity.
    • Existing 3D semantic segmentation methods often neglect valuable 2D data and struggle with noisy pseudo-labels.
    • Advancements in 2D foundation models offer powerful segmentation capabilities.

    Purpose of the Study:

    • To improve 3D semantic segmentation performance with limited annotations.
    • To effectively integrate information from 2D foundation models into 3D segmentation tasks.
    • To overcome limitations of existing label extension and pseudo-labeling techniques.

    Main Methods:

    • Incorporating segmentation masks from 2D foundation models into 3D segmentation.
    • Propagating 2D masks to 3D space via geometric correspondences.

    More Related Videos

    Volume Segmentation and Analysis of Biological Materials Using SuRVoS (Super-region Volume Segmentation) Workbench
    11:38

    Volume Segmentation and Analysis of Biological Materials Using SuRVoS (Super-region Volume Segmentation) Workbench

    Published on: August 23, 2017

    Related Experiment Videos

    Last Updated: May 16, 2026

    Automated Joint Space Detection Improves Bone Segmentation Accuracy
    06:45

    Automated Joint Space Detection Improves Bone Segmentation Accuracy

    Published on: November 28, 2025

    Volume Segmentation and Analysis of Biological Materials Using SuRVoS (Super-region Volume Segmentation) Workbench
    11:38

    Volume Segmentation and Analysis of Biological Materials Using SuRVoS (Super-region Volume Segmentation) Workbench

    Published on: August 23, 2017

  • Augmenting sparse 3D annotations using 3D masks and confidence-based regularization for pseudo-label generation.

    • Main Results:

    • Significantly increased the pool of available labels for 3D segmentation.
    • Successfully leveraged 2D foundation models to enhance 3D segmentation.
    • Improved the performance of weakly supervised 3D semantic segmentation.

    Conclusions:

    • The proposed method effectively bridges the gap between limited 3D annotations and powerful 2D foundation models.
    • This approach offers a robust solution for 3D semantic segmentation in data-scarce scenarios.
    • The strategy enhances label utilization and pseudo-label reliability for better segmentation outcomes.