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
02/12/2025
The lightweight and highly portable CORVUS-RAVEN, recently demonstrated at the V...
02/12/2025
The lightweight, rugged Panther 2 tri-band VSAT delivers high-speed data communications for Internet, VPN connectivity and video transmission over commercial an...
02/12/2025
NGID volunteers in the United States
NGID volunteers in Mexico
NGID volunteers in India
NGID volunteers in Spain
NGID volunteers in Australia
NGID voluntee...
02/12/2025
WASHINGTON The Federal Communications Commission's Media Bureau has issued a reminder that stations in DMAs 111 through 120 must implement its audio descrip...
02/12/2025
SAN DIEGO Sony Electronics today introduced the Alpha 7 V (ILCE-7M5), the fifth generation of its Alpha 7 full-frame mirrorless lineup, powered by the newly dev...
02/12/2025
WASHINGTON The Federal Communications Commission has opened a docket for comments on Nexstar Media Group's proposed $6.2 billion acquisition of Tegna and se...
02/12/2025
WASHINGTON The National Association of Broadcasters has added a trio of media executives, Veronica Rodriguez, Matt Schnaars and Jeff Warshaw, to its board of di...
02/12/2025
MILAN, Italy Brightcove has released seven new features designed to expand global reach, improve audience engagement, enhance live-streaming quality and streaml...
02/12/2025
BCNEXXT, the developers of the advanced playout platform Vipe, today announced a new Service Provider Partner agreement with NPC Media, the Australian managed p...
02/12/2025
DPA Microphones today announces the immediate availability of its new N-Series Digital Wireless Microphone System for customers throughout the U.S. In addition ...
02/12/2025
Hiltron Communications reports a well attended and successful Space Tech Expo exhibition, held at the Messe Bremen from Tuesday November 18 through Thursday Nov...
02/12/2025
The beginning of September saw Riverfire by Australian Retirement Trust, in association with Channel 9 and Triple M, kick off the 2025 Brisbane Festival in spec...
02/12/2025
SGM Lighting is pleased to announce an exciting new partnership with ACT Entertainment, under which ACT will serve as the exclusive distributor for SGM's ne...
02/12/2025
Harmonic (NASDAQ: HLIT) today announced that Telia, the second largest telecom operator in Norway, is modernizing its broadband network with the company's i...
02/12/2025
European cloud data protection specialist Keepit is expanding its sales network in the DACH region and has gained TIM AG, one of the leading value-added distrib...
02/12/2025
Featured products at ISE 2026
This year s ISE 2026 theme "Push Beyond" reflects Calrec s direction of travel. The company is dedicated to supporting the AV an...
02/12/2025
Czech Television, the national public broadcaster, has deployed one of the largest LiveU live production projects in the region for live sports and news coverag...
02/12/2025
Test & measurement innovator, Leader Electronics, has announced the release of v8.2 software for its ZEN and ZEN-W Series, bringing advanced cinematic camera se...
02/12/2025
Global provider of video streaming software and services, Accedo, and OTT platform provider, Magine Pro, have signed a binding agreement to carve out and merge ...
02/12/2025
With proven success in broadcast, OTT, and content supply chains, K.S Avinash set to scale Skandha's service-first approach across APAC
Skandha Media Servi...
02/12/2025
AJA Video Systems has joined the RAVENNA community, a network of partners devoted to advancing the RAVENNA standard for distributing real-time audio over intern...
02/12/2025
HUNT VALLEY, Md. Sinclair and its wholly-owned subsidiary One Media Technologies have released a new report focused on how ATSC 3.0, the IP-based NextGen TV sta...
02/12/2025
WASHINGTON The Federal Communications Commission's Media Bureau has issued a reminder that stations in DMAs 111 through 120 must implement its audio descrip...
02/12/2025
WASHINGTON Members of the Advanced Television Systems Committee have elected four industry veterans to three-year terms on the organization's board of direc...
02/12/2025
A new survey from S&P Global Market Intelligence Kagan highlights how important social media is for younger consumers, with Gen Z spending 5.1 hours a day on so...
02/12/2025
Faculty Notes: Fall/Winter 2025 Recent accomplishments, releases, and events by Berklee faculty.
December 1, 2025
By
Editorial Staff
The cast of Kind of M...
02/12/2025
Back to All News
Made in America: How Stranger Things' Electrified the US Economy
Entertainment
02 December 2025
GlobalUnited States
Link copied to cl...
02/12/2025
Back to All News
Culinary Class Wars' Season 2 Trailer Teases New Rules, R...
02/12/2025
At AWS re:Invent, NVIDIA and Amazon Web Services expanded their strategic collab...
01/12/2025
L3Harris and PentenAmio formalise their teaming agreement at MilCIS 2025, streng...
01/12/2025
Artemis II is NASA's first crewed flight test of the Space Launch System rocket and Orion spacecraft. The crew, from left: Commander Reid Wiseman, Pilot Vic...
01/12/2025
IRVINE, Calif. Wooden Camera has introduced its new Accessory Collection for the Canon EOS C50. The new lineup includes a low-profile, gimbal-ready cage, expand...
01/12/2025
WASHINGTON The Federal Communications Commission has released a tentative agenda for its Dec. 18 Open Commission Meeting that will include a vote on a report an...
01/12/2025
In most years, a graph of annual local TV ad spending is about as predictable as an electrocardiogram of a reasonably healthy patient in a doctor's office. ...
01/12/2025
Many industries have seen big-ticket hardware turn into software. Switchers, though, demand a combination of real-time performance and sheer bandwidth that has ...
01/12/2025
GENEVA Shanghai will host the next quadrennial Radiocommunication Assembly (RA-27) and World Radiocommunication Conference (WRC-27), Oct. 11-Nov. 12, 2027. This...
01/12/2025
NEW YORK Just in time for Giving Tuesday tomorrow (Dec. 2), the Broadcasters Foundation of America is seeking out donations to help television and radio industr...
01/12/2025
STOCKHOLM, Sweden Net Insight CEO Crister Fritzson has informed the company's board that he will retire from the video transport and media cloud technology ...
01/12/2025
Back to All News
Netflix Unveils Hilarious, Heartwarming Trailer for Upcoming F...
01/12/2025
Back to All News
A Down to Earth, All Too Relatable Hero: Cashero' Teaser ...
01/12/2025
In the rush to deliver content to every screen, many broadcasters overlook one of the most crucial steps in the workflow: format and frame rate conversion. Get ...
01/12/2025
Researchers worldwide rely on open-source technologies as the foundation of their work. To equip the community with the latest advancements in digital and physi...
28/11/2025
Nadia Fall attends the 2025 Sundance Film Festival premiere of Brides at the Egyptian Theatre on January 24, 2025, in Park City, Utah. (Photo by Donyale West/...
28/11/2025
WASHINGTON Federal Communications Commission has released a tentative agenda for the December Open Commission Meeting scheduled for Thursday, December 18, 2025 ...
28/11/2025
The Professional Fighters League is looking to super-serve fans of mixed martial...
28/11/2025
Fubo has released in beta on select Roku devices a new feature that lets users display up to four simultaneous streams at once....
28/11/2025
The WNBA playoffs and Week 4 of the NFL regular season highlight the list of live sports events airing on television this weekend....
28/11/2025
The 32nd class of honorees to the B+C Hall of Fame took to the stage at New York's Ziegfeld Ballroom on September 26 for a gala induction event. Click below...
28/11/2025
We hold in our hands the very last Next Text for Next TV, the weekly back-and-fo...
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.
