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

Self-Supervised Text-Driven Point Cloud Upsampling via Semantic Text Guidance.

Zhiyong Zhang1, Meiling Qiu1, Shuo Chen1

  • 1School of Computer Science and Engineering, Tianjin University of Technology, Tianjin 300000, China.

Journal of Imaging
|May 26, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Upsampling01:22

Upsampling

Managing signal sampling rates is essential in digital signal processing to maintain signal integrity. A decimated signal, characterized by a reduced frequency range due to its lower sampling rate, can be upsampled by inserting zeros between each sample. This upsampling process expands the original spectrum and introduces repeated spectral replicas at intervals dictated by the new Nyquist frequency. To refine this zero-inserted sequence, it is passed through a lowpass filter with a cutoff...

You might also read

Related Articles

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

Sort by
Same author

Cholinergic Basal Forebrain Atrophy Accelerates Cognitive Decline via Cortical Thinning: The Moderating Role of Amyloid-β Pathology in Preclinical Alzheimer's Disease.

Research square·2026
Same author

Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks, Challenges and Baselines.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Time-Frequency Collaborative Learning for Imbalanced Ship Motion Data With Missing Labels in Sea State Estimation.

IEEE transactions on cybernetics·2025
Same author

Correction: Physical activity and internalization problems in middle school students: the chain mediating role of rumination thinking and peer acceptance.

Scientific reports·2025
Same author

Cholinergic basal forebrain atrophy accelerates cognitive decline via cortical thinning: The moderating role of amyloid-β pathology in preclinical Alzheimer's disease.

The journal of prevention of Alzheimer's disease·2025
Same author

Multimodal Navigation and Virtual Companion System: A Wearable Device Assisting Blind People in Independent Travel.

Sensors (Basel, Switzerland)·2025
Same journal

Human-AI Interaction in Interventional Radiology: A Narrative Review of Current Applications, Challenges, and Future Directions.

Journal of imaging·2026
Same journal

Coronary Artery Anomalies and Anatomical Variants: Cross-Sectional Diagnostic Imaging and Clinical Background.

Journal of imaging·2026
Same journal

YoLeTooth: A Unified Framework for Joint Tooth Segmentation and Periapical Lesion Detection in Panoramic Radiographs.

Journal of imaging·2026
Same journal

Radiomics-Guided Multi-Sequence Learning for Pathological Complete Response Prediction from Breast MRI with Missing Auxiliary Sequences.

Journal of imaging·2026
Same journal

Cutaneous Thermography in Arthropathies: Quantitative Imaging, Machine Learning, and Clinical Translation.

Journal of imaging·2026
Same journal

Two-Stage Dynamic Synergistic Segmentation Method for Myocardial Pathology.

Journal of imaging·2026
See all related articles

PartSPUNet enhances 3D robotic perception by using text prompts for targeted point cloud upsampling. This self-supervised method refines specific regions, improving detail recovery for intelligent systems.

Area of Science:

  • Computer Vision
  • Robotics
  • Artificial Intelligence

Background:

  • Point cloud upsampling is crucial for 3D vision tasks.
  • Existing methods often use inefficient global strategies.
  • There is a need for region-specific refinement in point cloud processing.

Purpose of the Study:

  • To introduce PartSPUNet, a novel self-supervised framework for text-driven point cloud upsampling.
  • To enable task-oriented local refinement for enhanced robotic perception.
  • To leverage natural language prompts for intuitive control over the upsampling process.

Main Methods:

  • Utilizes a pretrained vision-language model for zero-shot semantic part localization.
  • Performs geometry-aware densification focused on user-specified regions.
Keywords:
biomimetic perceptionlanguage-guidedpoint cloud upsamplingvision–language model

Related Experiment Videos

  • Employs a self-supervised, text-driven approach for local refinement.

    • Main Results:

    • PartSPUNet significantly outperforms existing methods in reconstructing specified areas.
    • The framework successfully recovers rich geometric details in targeted regions.
    • Global structure is preserved while local regions are densified.

    Conclusions:

    • PartSPUNet offers a powerful and intuitive tool for enhancing 3D perception pipelines.
    • The text-driven local refinement approach improves robotic perception capabilities.
    • This method provides efficient and targeted upsampling for complex 3D data.