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 10, 2026

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
09:41

Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

Published on: April 21, 2023

MVHumanNet++: A Large-scale Dataset of Multi-view Daily Dressing Human Captures with Richer Annotations for 3D Human

Chenghong Li, Hongjie Liao, Yihao Zhi

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |May 8, 2026
    PubMed
    Summary

    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

    Dual-hook clip closure for high-tension gastric defects.

    Endoscopy·2026
    Same author

    Spontaneous Room-Temperature Polymerization of Carbon Disulfide in Water Microdroplets.

    Journal of the American Chemical Society·2026
    Same author

    TransIA: A transformer-based few-shot learning framework for detecting PDE5 inhibitor derivatives.

    Journal of hazardous materials·2026
    Same author

    Rigid side-hole cap-assisted guidewire fragmentation of giant gastric bezoars.

    Endoscopy·2026
    Same author

    Pulmonary artery involvement contributes to the recurrence of hemoptysis after bronchial artery embolization in patients with chronic pulmonary aspergillosis.

    Journal of thoracic disease·2026
    Same author

    Clinical significance of serum levels of 14-3-3β protein in patients with non-small cell lung cancer.

    Scientific reports·2026

    The new MVHumanNet++ dataset provides large-scale 3D human data for computer vision research. This multi-view human dataset features diverse identities and clothing, enabling advancements in 3D human-centric tasks.

    Area of Science:

    • Computer Vision
    • 3D Human-Centric Research

    Background:

    • Large-scale datasets drive progress in AI, particularly for 3D vision object-centric tasks.
    • Human-centric 3D vision tasks lag due to a lack of comparable large-scale human datasets.

    Purpose of the Study:

    • Introduce MVHumanNet++, the largest-scale 3D human dataset to date.
    • Address the gap in large-scale multi-view human action sequence data.
    • Facilitate advancements in 3D human-centric computer vision research.

    Main Methods:

    • Collected multi-view human action sequences from 4,500 identities.
    • Captured diverse everyday clothing and daily outfits.
    • Utilized multi-view human capture systems for scalable data collection.

    Main Results:

    Related Experiment Videos

    Last Updated: May 10, 2026

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping
    09:41

    Estimation of Contact Regions Between Hands and Objects During Human Multi-Digit Grasping

    Published on: April 21, 2023

    • MVHumanNet++ contains 9,000 outfits, 60,000 motion sequences, and 645 million frames.
    • Dataset includes extensive annotations: masks, camera parameters, 2D/3D keypoints, SMPL/SMPLX parameters, and text descriptions.
    • Enhanced with processed normal and depth maps for broader applicability.

    Conclusions:

    • MVHumanNet++ is the largest-scale 3D human dataset available.
    • Pilot studies demonstrate performance improvements in 2D and 3D visual tasks.
    • The dataset aims to foster innovation in large-scale 3D human-centric research.