3D Scanning SevicesAM SoftwareVideoVirtual Reality

There is an AI that can make a 3D model of a person from short video clips | video

Stay up to date with everything that is happening in the wonderful world of AM via our LinkedIn community.

A paper that was just submitted to the Cornell University Library describes how to obtain accurate 3D body models and texture of arbitrary people from a single, monocular video in which a person is moving. The paper was authored by Thiemo Alldieck, Marcus Magnor, Weipeng Xu, Christian Theobalt and Gerard Pons-Moll; it will be presented at the upcoming Computer Vision and Pattern Recognition conference in Salt Lake City.

Based on a parametric body model, the researchers present a robust processing pipeline achieving 3D model fits with 5 mm accuracy, for clothed people as well. The authors’ main contribution is a method to non-rigidly deform the silhouette cones corresponding to the dynamic human silhouettes, resulting in a visual hull in a common reference frame that enables surface reconstruction.

As Sciencemag – that first reported the news – explains, the system has three stages: “First, it analyzes a video a few seconds long of someone moving—preferably turning 360° to show all sides—and for each frame creates a silhouette separating the person from the background. Based on machine learning techniques—in which computers learn a task from many examples—it roughly estimates the 3D body shape and location of joints. In the second stage, it “unposes” the virtual human created from each frame, making them all stand with arms out in a T shape, and combines information about the T-posed people into one, more accurate model. Finally, in the third stage, it applies color and texture to the model based on recorded hair, clothing, and skin.”

AI 3d model from video

This enables efficient estimation of a consensus 3D shape, texture and implanted animation skeleton based on a large number of frames. The researchers presented evaluation results for a number of test subjects and analyzed overall performance. Requiring only a smartphone or webcam, this method enables everyone to create their own fully animatable digital double.

This system can be used for integration in 3D software programs such as video games or 3D animations, for social VR applications or virtual try-on for online fashion shopping. Eventually, it could easily be modified to export accurate 3D models, ending the ongoing dilemma of how to give someone a 3D replica of themselves as a surprise gift.

Via Sciencemag

Composites AM 2024

746 composites AM companies individually surveyed and studied. Core composites AM market generated over $785 million in 2023. Market expected to grow to $7.8 billion by 2033 at 25.8% CAGR. This new...


VoxelMatters is the online trade media portal published by 3dpbm, a leading marketing and market research firm specializing in the AM industry. 3dpbm also publishes the 3D Printing Business Directory, the AM Focus eBook series and the 3dpbm Research AM Market Reports. 3D Printing Media Network was founded with the goal to provide the latest industry news, insights and opinions to a global audience of professionals and decision makers.

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button
Close Popup
Privacy Settings saved!
Privacy Settings

When you visit any web site, it may store or retrieve information on your browser, mostly in the form of cookies. Control your personal Cookie Services here.

These cookies are necessary for the website to function and cannot be switched off in our systems.

Technical Cookies
In order to use this website we use the following technically required cookies
  • wordpress_test_cookie
  • wordpress_logged_in_
  • wordpress_sec

Decline all Services
Accept all Services


Join our 12,000+ Professional community and get weekly AM industry insights straight to your inbox. Our editor-curated newsletter equips executives, engineers, and end-users with crucial updates, helping you stay ahead.