Fasten your seatbelts. NVIDIA Research is revving up a new deep learning engine that creates 3D object models from standard 2D images - and can bring iconic cars like the Knight Rider's AI-powered KITT to life - in NVIDIA Omniverse.
Developed by the NVIDIA AI Research Lab in Toronto, the GANverse3D application inflates flat images into realistic 3D models that can be visualized and controlled in virtual environments. This capability could help architects, creators, game developers and designers easily add new objects to their mockups without needing expertise in 3D modeling, or a large budget to spend on renderings.
A single photo of a car, for example, could be turned into a 3D model that can drive around a virtual scene, complete with realistic headlights, tail lights and blinkers.
To generate a dataset for training, the researchers harnessed a generative adversarial network, or GAN, to synthesize images depicting the same object from multiple viewpoints - like a photographer who walks around a parked vehicle, taking shots from different angles. These multi-view images were plugged into a rendering framework for inverse graphics, the process of inferring 3D mesh models from 2D images.
Once trained on multi-view images, GANverse3D needs only a single 2D image to predict a 3D mesh model. This model can be used with a 3D neural renderer that gives developers control to customize objects and swap out backgrounds.
When imported as an extension in the NVIDIA Omniverse platform and run on NVIDIA RTX GPUs, GANverse3D can be used to recreate any 2D image into 3D - like the beloved crime-fighting car KITT, from the popular 1980s Knight Rider TV show.
Previous models for inverse graphics have relied on 3D shapes as training data.
Instead, with no aid from 3D assets, We turned a GAN model into a very efficient data generator so we can create 3D objects from any 2D image on the web, said Wenzheng Chen, research scientist at NVIDIA and lead author on the project.
Because we trained on real images instead of the typical pipeline, which relies on synthetic data, the AI model generalizes better to real-world applications, said NVIDIA researcher Jun Gao, an author on the project.
The research behind GANverse3D will be presented at two upcoming conferences: the International Conference on Learning Representations in May, and the Conference on Computer Vision and Pattern Recognition, in June.
From Flat Tire to Racing KITT Creators in gaming, architecture and design rely on virtual environments like the NVIDIA Omniverse simulation and collaboration platform to test out new ideas and visualize prototypes before creating their final products. With Omniverse Connectors, developers can use their preferred 3D applications in Omniverse to simulate complex virtual worlds with real-time ray tracing.
But not every creator has the time and resources to create 3D models of every object they sketch. The cost of capturing the number of multi-view images necessary to render a showroom's worth of cars, or a street's worth of buildings, can be prohibitive.
That's where a trained GANverse3D application can be used to convert standard images of a car, a building or even a horse into a 3D figure that can be customized and animated in Omniverse.
To recreate KITT, the researchers simply fed the trained model an image of the car, letting GANverse3D predict a corresponding 3D textured mesh, as well as different parts of the vehicle such as wheels and headlights. They then used NVIDIA Omniverse Kit and NVIDIA PhysX tools to convert the predicted texture into high-quality materials that give KITT a more realistic look and feel, and placed it in a dynamic driving sequence.
Omniverse allows researchers to bring exciting, cutting-edge research directly to creators and end users, said Jean-Francois Lafleche, deep learning engineer at NVIDIA. Offering GANverse3D as an extension in Omniverse will help artists create richer virtual worlds for game development, city planning or even training new machine learning models.
GANs Power a Dimensional Shift Because real-world datasets that capture the same object from different angles are rare, most AI tools that convert images from 2D to 3D are trained using synthetic 3D datasets like ShapeNet.
To obtain multi-view images from real-world data - like images of cars available publicly on the web - the NVIDIA researchers instead turned to a GAN model, manipulating its neural network layers to turn it into a data generator.
The team found that opening the first four layers of the neural network and freezing the remaining 12 caused the GAN to render images of the same object from different viewpoints.
Keeping the first four layers frozen and the other 12 layers variable caused the neural network to generate different images from the same viewpoint. By manually assigning standard viewpoints, with vehicles pictured at a specific elevation and camera distance, the researchers could rapidly generate a multi-view dataset from individual 2D images.
The final model, trained on 55,000 car images generated by the GAN, outperformed an inverse graphics network trained on the popular Pascal3D dataset.
Read the full ICLR paper, authored by Wenzheng Chen, fellow NVIDIA researchers Jun Gao and Huan Ling, Sanja Fidler, director of NVIDIA's Toronto research lab, University of Waterloo student Yuxuan Zhang, Stanford student Yinan Zhang and MIT professor Antonio Torralba. Additional collaborators on the CVPR paper include Jean-Francois Lafleche, NVIDIA researcher Kangxue Yin and Adela Barriuso.
The NVIDIA Research team consists of more than 200 scientists around the globe, focusing on areas such as AI, computer vision, self-driving cars, robotics and graphics. Learn more about the company's latest research and industry breakthroughs in NVIDIA CEO Jensen Huang's k
North America Stories
19/05/2026
Cisco and the USGA have announced a multiyear extension of their partnership, which began in 2018. Cisco serves as the Official Technology Partner of the USGA, ...
19/05/2026
Urban Edge Network (UEN), a streaming platform for NAIA sports, has announced a partnership with Spiideo to provide streaming and production tools to UEN's ...
19/05/2026
Warner Bros. Discovery (WBD) will provide live coverage of all 900 Roland-Garros matches across its platforms beginning with qualifiers on May 18. In Europe, 21...
19/05/2026
Tubi, Fox Corporation's free streaming service, has announced the launch of the FIFA World Cup 2026 FOX Hub, a dedicated destination for World Cup programmi...
19/05/2026
Telef nica, in collaboration with Sony, has conducted a 5G connectivity trial at the Movistar Arena in Spain using the 26 GHz millimetre wave (mmWave) band. The...
19/05/2026
Ross Production Services (RPS) has installed a Calrec Argo M console into its new Hypermax-1 remote production truck, replacing one of three Argo S consoles pre...
19/05/2026
Panasonic Projector and Display Corporation has announced the acquisition of 100% of the shares of UK-based media technology company Hive Media Control Ltd. (HI...
19/05/2026
Globecast has announced the completion of a nine-month renovation of its Singapore facility, converting it from a traditional linear broadcast operation into a ...
19/05/2026
Grass Valley has announced a three-year enterprise agreement with Phoenix Broadc...
19/05/2026
Bitmovin has announced that Watch Brasil, a streaming platform operating across Brazil and Europe since 2018, has replaced its legacy systems with Bitmovin'...
19/05/2026
Ateme has announced the migration of Dish Home Nepal's Nepal Premier League (NPL) streaming infrastructure to Ateme's TITAN Live solution deployed on Ak...
19/05/2026
CMSI provided workflow, media management, and HDR support for ESPN during coverage of the NCAA Gymnastics Semifinals and Championships. The company supported fi...
19/05/2026
In advance of this year's Sports Emmy Awards, SVG is taking a deep dive into the six production-technologies nominated for this year's George Wensel Tec...
19/05/2026
In advance of this year's Sports Emmy Awards, SVG is taking a deep dive into the six production-technologies nominated for this year's George Wensel Tec...
19/05/2026
Featuring a fully IP infrastructure, Supershooter 11 is intended for large-scale events. Enabling remote and distributed workflows, Supershooter 65 joins the RE...
19/05/2026
By Jessica Herndon
The line wrapped around the building outside Denver's La...
19/05/2026
When all companies in the market are allowed to compete under the same set of ru...
19/05/2026
Battle-proven technology withstands electronic warfare threats across air, maritime surface and subsea domains....
19/05/2026
WESCAM MX-Series EO/IR systems provide high-precision targeting across domains, including counter-UAS applications...
19/05/2026
Champaign, IL - March 16, 2026 Cobalt Digital, the leading designer and manufa...
19/05/2026
CHAMPAIGN, Ill. April 16, 2026 - Cobalt Digital today announced a partnership ...
19/05/2026
Las Vegas - April 18, 2026 Cobalt Digital, the leading designer and manufactur...
19/05/2026
LAS VEGAS April 18, 2026 - Advanced HDR by Technicolor and Cobalt Digital are ...
19/05/2026
LAS VEGAS - May 4, 2026 - Cobalt Digital, the leading designer and manufacturer of signal processing products, and a founding partner in the openGear initiativ...
19/05/2026
London - 11 May 2026 Cobalt Digital, the leading designer and manufacturer of award-winning signal processing products, and a founding partner in the openGear...
19/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/05/2026
Grass Valley has entered into a three-year enterprise agreement with Phoenix Broadcast Solutions as the Singapore-based company expands its live production oper...
19/05/2026
Clear-Com supported Musikal Perahu Kertas, a large-scale musical theater production in Indonesia adapted from the acclaimed novel by Dee Lestari, through the d...
19/05/2026
Actus Digital, a LiveU company, and a leading provider of intelligent media monitoring and broadcast compliance platforms, announced today that METEO CONSULT ha...
19/05/2026
Globecast, a leading provider of managed services for the broadcast and media industry, today announced the completion of a major renovation of its Singapore fa...
19/05/2026
Following a major upgrade to its Connecticut remote production centre with the installation of three 60-fader Argo S consoles in 2023, RPS has switched one of t...
19/05/2026
PlayBox Technology today announced the launch of Celebro Play, a browser-based media orchestration platform designed specifically for broadcast facilities and p...
19/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/05/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
19/05/2026
LYNX Technik, provider of modular signal processing solutions for broadcast, post, and professional AV will showcase its latest signal processing solutions at B...
19/05/2026
Media Links, a leading developer and manufacturer of IP media transport solutions, has announced the integration of its Xscend platform with Skyline Communicat...
19/05/2026
Collaboration expands regional partner ecosystem as Media Links showcases IP media transport solutions on stand 4M4-4 and alongside Clearcast Asia on stand
Me...
19/05/2026
Company Highlights Labor-Saving Control and Custom Branding Opportunities Designed to Increase Integrator Profitability
LynTec, a leading manufacturer of ele...
19/05/2026
Mago Studio Moves AI Video Beyond Prompts with New Production-Focused Tools
Brie Clayton May 18, 2026
0 Comments
New Capabilities Bring Controllable, ...
19/05/2026
It May be Time to Stop and Take an AI Breather
Brie Clayton May 19, 2026
0 Comments
If the rock you stay on starts to roll, jump clean. Or you'll...
19/05/2026
Back to All News
Netflix Unveils the Trailer for RAFA, the Documentary Series A...
19/05/2026
Back to All News
Netflix Expands Consumer Products Footprint with Strategic Con...
19/05/2026
Matt Derella Expands Leadership Across LinkedIn Ads and Microsoft Advertising Published on May 19, 2026 Categories: Company News
LinkedIn Corporate Commun...
18/05/2026
Despite a bumpy start to the year, the provider of event-production support and ...
18/05/2026
Daktronics has partnered with the University of North Carolina to manufacture and install 11 LED displays totaling more than 10,000 square feet and more than 14...
18/05/2026
CBS LA has announced a multi-year partnership with the Los Angeles Rams, covering exclusive local broadcasts of Rams preseason games, weekly year-round programm...
Fasten your seatbelts. NVIDIA Research is revving up a new deep learning engine that creates 3D object models from standard 2D images - and can bring iconic cars like the Knight Rider's AI-powered KITT to life - in NVIDIA Omniverse.
