
NVIDIA researchers are at the forefront of the rapidly advancing field of visual generative AI, developing new techniques to create and interpret images, videos and 3D environments.
More than 50 of these projects will be showcased at the Computer Vision and Pattern Recognition (CVPR) conference, taking place June 17-21 in Seattle. Two of the papers - one on the training dynamics of diffusion models and another on high-definition maps for autonomous vehicles - are finalists for CVPR's Best Paper Awards.
NVIDIA is also the winner of the CVPR Autonomous Grand Challenge's End-to-End Driving at Scale track - a significant milestone that demonstrates the company's use of generative AI for comprehensive self-driving models. The winning submission, which outperformed more than 450 entries worldwide, also received CVPR's Innovation Award.
NVIDIA's research at CVPR includes a text-to-image model that can be easily customized to depict a specific object or character, a new model for object pose estimation, a technique to edit neural radiance fields (NeRFs) and a visual language model that can understand memes. Additional papers introduce domain-specific innovations for industries including automotive, healthcare and robotics.
Collectively, the work introduces powerful AI models that could enable creators to more quickly bring their artistic visions to life, accelerate the training of autonomous robots for manufacturing, and support healthcare professionals by helping process radiology reports.
Artificial intelligence, and generative AI in particular, represents a pivotal technological advancement, said Jan Kautz, vice president of learning and perception research at NVIDIA. At CVPR, NVIDIA Research is sharing how we're pushing the boundaries of what's possible - from powerful image generation models that could supercharge professional creators to autonomous driving software that could help enable next-generation self-driving cars.
At CVPR, NVIDIA also announced NVIDIA Omniverse Cloud Sensor RTX, a set of microservices that enable physically accurate sensor simulation to accelerate the development of fully autonomous machines of every kind.
Forget Fine-Tuning: JeDi Simplifies Custom Image Generation Creators harnessing diffusion models, the most popular method for generating images based on text prompts, often have a specific character or object in mind - they may, for example, be developing a storyboard around an animated mouse or brainstorming an ad campaign for a specific toy.
Prior research has enabled these creators to personalize the output of diffusion models to focus on a specific subject using fine-tuning - where a user trains the model on a custom dataset - but the process can be time-consuming and inaccessible for general users.
JeDi, a paper by researchers from Johns Hopkins University, Toyota Technological Institute at Chicago and NVIDIA, proposes a new technique that allows users to easily personalize the output of a diffusion model within a couple of seconds using reference images. The team found that the model achieves state-of-the-art quality, significantly outperforming existing fine-tuning-based and fine-tuning-free methods.
JeDi can also be combined with retrieval-augmented generation, or RAG, to generate visuals specific to a database, such as a brand's product catalog.
https://blogs.nvidia.com/wp-content/uploads/2024/06/JeDi-cow-sculpture.mp4
New Foundation Model Perfects the Pose NVIDIA researchers at CVPR are also presenting FoundationPose, a foundation model for object pose estimation and tracking that can be instantly applied to new objects during inference, without the need for fine-tuning.
The model, which set a new record on a popular benchmark for object pose estimation, uses either a small set of reference images or a 3D representation of an object to understand its shape. It can then identify and track how that object moves and rotates in 3D across a video, even in poor lighting conditions or complex scenes with visual obstructions.
FoundationPose could be used in industrial applications to help autonomous robots identify and track the objects they interact with. It could also be used in augmented reality applications where an AI model is used to overlay visuals on a live scene.
NeRFDeformer Transforms 3D Scenes With a Single Snapshot A NeRF is an AI model that can render a 3D scene based on a series of 2D images taken from different positions in the environment. In fields like robotics, NeRFs can be used to generate immersive 3D renders of complex real-world scenes, such as a cluttered room or a construction site. However, to make any changes, developers would need to manually define how the scene has transformed - or remake the NeRF entirely.
Researchers from the University of Illinois Urbana-Champaign and NVIDIA have simplified the process with NeRFDeformer. The method, being presented at CVPR, can successfully transform an existing NeRF using a single RGB-D image, which is a combination of a normal photo and a depth map that captures how far each object in a scene is from the camera.
VILA Visual Language Model Gets the Picture A CVPR research collaboration between NVIDIA and the Massachusetts Institute of Technology is advancing the state of the art for vision language models, which are generative AI models that can process videos, images and text.
The group developed VILA, a family of open-source visual language models that outperforms prior neural networks on key benchmarks that test how well AI models answer questions about images. VILA's unique pretraining process unlocked new model capabilities, including enhanced world knowledge, stronger in-context learning and the ability to reason across multiple images.
VILA can understand memes and reason based on multiple images or video frames. The VILA model fa
North America Stories
23/01/2026
ALT Systems, Inc., a leading system integrator and technology solutions provider for the media and entertainment industry, today announced the launch of PixSpan...
23/01/2026
The Alliance for IP Media Solutions (AIMS) will mark a major milestone for Pro AV-over-IP at ISE 2026 with the official launch of Internet Protocol Media Experi...
23/01/2026
KRK, a leader in professional studio monitoring for nearly four decades, will unveil the all new V Series Five at the 2026 NAMM Show, offering attendees an excl...
23/01/2026
SMPTE , the home of media professionals, technologists, and engineers, today announced Steve LLamb, Vice President of Technology Standards and Solutions for Cin...
23/01/2026
IBC today announces that the call for Technical Papers is now open for the IBC2026 Conference, inviting innovators from across the global media, entertainment, ...
23/01/2026
Grass Valley has announced that Asharq News, the leading multi-platform Arabic news service owned by the Saudi Research & Media Group (SRMG), has expanded its c...
23/01/2026
At the SET Expo 2025, a consortium including Qualcomm Technologies, Inc., Motorola, and Rohde & Schwarz successfully demonstrated a real-world proof-of-concept ...
23/01/2026
Dalet, a leading technology and service provider for media-rich organizations, today announced the appointment of Gwen Braygreen as Executive Vice President and...
23/01/2026
Alfalite, Brainstorm, Dejero, Domo Broadcast Systems, FOR-A, KitPlus, Ontario Soluciones and RGB Spectrum partner to demonstrate revolutionary integrated soluti...
23/01/2026
Vizrt, the leader in live production technology revolutionizing viewer experience and engagement, expands its team to ignite a new era of professional-grade pro...
23/01/2026
LOGIC media solutions, an Amazon Web Services (AWS) Advanced Partner specialising in AWS-based media workflows, is one of the official launch partners of the ne...
23/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
23/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
23/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
23/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
23/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
23/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
23/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
22/01/2026
SVG Students To Watch: Chuck Luarasi, Curry CollegeThe Massachusetts native is cutting his teeth with Harvard Athletics, Cape Cod Baseball LeagueBy Brandon Cost...
22/01/2026
Follow the Money, Episode 4: Talking Tech, Sports, and Private Capital With Sam ...
22/01/2026
Fever pitch: WRC is back for the start of the 2026 season with Rallye Monte-Carl...
22/01/2026
FloSports Prepares To Broadcast Outdoor Hockey Game Amidst Brutally Cold Tempera...
22/01/2026
As Paramount Enters the Octagon, UFC's Craig Borsari Previews Production Pl...
22/01/2026
By Jordan Crucchiola
It's a desire you hear so often among those in filmmaking circles. I just want to make cool stuff with my friends. With the NEXT selec...
22/01/2026
Brittany Shyne attends the 2025 Sundance Film Festival premiere of Seeds at The Ray Theatre on January 25, 2025, in Park City, UT. (Photo by Robin Marshall/Sh...
22/01/2026
Joel Edgerton and Felicity Jones appear in Train Dreams by Clint Bentley, an off...
22/01/2026
MELBOURNE, Fla., Jan 22, 2026 - L3Harris Technologies (NYSE: LHX) has received a...
22/01/2026
Strategic hire marks latest milestone in Gracenote's continued expansion into CTV advertising & monetization
New York - January 21, 2026 - Nielsen's Gr...
22/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
22/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
22/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
22/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
22/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
22/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
22/01/2026
AI-powered driver assistance technologies are becoming standard equipment, funda...
22/01/2026
A Four-Time Emmy Award Winner on Defining His SoundCharles David Denler is a Composer and Pianist for film, television, and the Concert Stage. He is a 4 Time E...
22/01/2026
The wait is over, pilots. Flight control support - one of the most community-requested features for GeForce NOW - is live starting today, following its announce...
22/01/2026
AI has taken center stage in financial services, automating the research and exe...
22/01/2026
AI-powered content generation is now embedded in everyday tools like Adobe and Canva, with a slew of agencies and studios incorporating the technology into thei...
21/01/2026
The Living Room Remains Central: Nielsen Highlights Growing TV Screen Dominance ...
21/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
21/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
21/01/2026
Share Share by:
Copy link
Facebook
X
Linkedin
Pinterest
Bluesky
Email...
21/01/2026
Telestream , the industry's leading provider of content lifecycle management and media workflow orchestration, and Quantum Corporation (NASDAQ: QMCO) today ...
21/01/2026
Lightware s TPN ecosystem brings a new level of predictability and structure to 10G AV-over-IP deployments, offering professional AV integrators a deterministic...
21/01/2026
Wisycom, a global leader in advanced wireless RF solutions, launches its new wideband antenna matrix, MATF, which supports RF and fiber for demanding multi-zone...
21/01/2026
Grass Valley will demonstrate how it is powering scalable, future-ready live production at FOMEX 2026, taking place February 2 4 in Riyadh, Saudi Arabia. Exhibi...
21/01/2026
BCNEXXT, the developers of the advanced playout platform Vipe, today announced that OKAST, the monetization-first OTT platform provider, is using BCNEXXT's ...
21/01/2026
Revamped design enables advanced capabilities, leading with powerful IP to HDMI conversion
Magewell, developer of innovative, high-performance video I/O and I...
21/01/2026
Jan 20th 2026, Changsha Kiloview today announced the launch of two major additions to its AV-over-IP ecosystem: the AVX24-4 Media HUB and KiloLink Station, ma...