Seamless in Seattle: NVIDIA Research Showcases Advancements in Visual Generative AI at CVPR

17/06/2024

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

LINK:	https://blogs.nvidia.com/blog/visual-generative-ai-cvpr-research/...
	See more stories from nvidia

North America Stories

17/07/2026

Foundry Unlocks Professional-Grade AI for VFX with Gripta...

Creative software developer Foundry today announced Griptape Enterprise, a new tier of the Griptape AI workflow orchestration platform, extended to meet the str...

17/07/2026

Foundry Releases SmartRoto for Nuke

Creative software developer Foundry today announced the availability of SmartRoto, a new AI-powered plugin upgrade for Nuke, NukeX, Nuke Studio, and Nuke Indie ...

17/07/2026

The Final Release of Blackmagic Fairlight Live is Now Available!

The Final Release of Blackmagic Fairlight Live is Now Available! Brie Clayton July 16, 2026 0 Comments Fairlight Live is a new audio mixer designed fo...

17/07/2026

Leveraging All of Entertainment's IP

Leveraging All of Entertainment's IP Andy Marken July 16, 2026 0 Comments Nobody ever wins the games. Period. There are survivors. There\s no win...

16/07/2026

SVG Students To Watch: Kaden Sherman, Albany State University

This recent graduate and Georgia native has turned an early fascination with live production into a growing passion for camera work In the live-sports-video in...

16/07/2026

TNDV Marks First Year of Aspiration 35 Cinematic Production Truck

TNDV is marking the first anniversary of Aspiration 35, a mobile production truck built around ARRI Alexa 35 Live camera systems. Over its first year, the truck...

16/07/2026

ATSC Releases First Major Revision to A/85 Audio Loudness Recommended Practice Since 2013

ATSC has completed a major revision to its A/85 Recommended Practice: Techniques...

16/07/2026

FloSports Named Exclusive Global Media Partner for 2026 CrossFit Games

FloSports has announced an exclusive global media partnership with CrossFit for the 2026 CrossFit Games, presented by Air National Guard, beginning July 21 in S...

16/07/2026

Sennheiser Releases Spectera Firmware 1.4 and Command Button

Sennheiser has released firmware version 1.4 for its Spectera wireless system and announced the Spectera Command Button (Cat. No. 701014). The update adds comma...

16/07/2026

ESPN and Southwestern Athletic Conference Announce Multi-Year Media Rights Agreement Through 2030-31

ESPN and the Southwestern Athletic Conference (SWAC) have announced a multi-year...

16/07/2026

Audio-Technica Releases 20 Series Control Application for Elgato Stream Deck

Audio-Technica has announced the 20 Series Control Application, a Stream Deck plug-in for compatible Audio-Technica USB microphones. The application is compatib...

16/07/2026

SSL Live L550 Plus Consoles Power Audio Production for The Voice France Season 15

The fifteenth season of The Voice - La plus belle voix on TF1 used four Solid St...

16/07/2026

Gray Media and Atlanta Hawks Announce Georgia-Wide Broadcast Partnership for 2026-27 NBA Season

Gray Media and the Atlanta Hawks have announced a broadcast partnership that wil...

16/07/2026

SVG Sit-Down: Quarterback Showrunner Joe Zucco on Cinematography, Building Trust, Carrying On the NFL Films Legacy

Season 3 of Netflix's docuseries, which dropped this week, follows Jayden Da...

16/07/2026

Texas Rangers Switch Direct-to-Consumer Streaming Partner to BZZR

The Texas Rangers and Rangers Sports Network presented by Progressive (RSN) have announced BZZR as the new direct-to-consumer distributor for Rangers game broad...

16/07/2026

FIFA World Cup 2026: BBC Sport on Moving Across the Pond to Bring the Atmosphere of the Final Matches to Fans

With England's FIFA World Cup 2026 team getting ready to fly home after losi...

16/07/2026

With 36 Unilateral Cameras, NBC Sports Shapes 154th Open Championship Coverage for U.S. Viewers

In a return to Royal Birkdale, the team enjoys partnering with ETP and Gravity M...

16/07/2026

Altitude Sports & Entertainment's Tim De Lay on New SkyCam Digital Feed, Upgraded Studio Space

Along with a new studio at Ball Arena, the Colorado-based RSN is working with XR...

16/07/2026

FIFA World Cup 2026: Inside ORF's Austria-Based Production to Bring All the Emotions of the Tournament to Fans

Austria was back at the World Cup for the first time in 28 years, and the team d...

16/07/2026

Inside Gravity Media's Effort To Power the 154th Open Championship Production

With 42 RF cameras and high-power radio mics deployed, the spectrum environment ...

16/07/2026

The Gauge: Poland | June 2026

June brought stabilization to the television market. Poles spent an average of 3 hours and 36 minutes a day in front of their TV screens exactly the same as i...

16/07/2026

New studio monitoring leads Glensound's 60th year line-up...

Glensound returns to IBC with a major new addition to its intelligent loudspeaker range, the Greater Divine Supernal studio monitor, alongside recent developmen...

16/07/2026

Complete spectrum of innovation from British exhibitors a...

33 leading exhibitors are taking part in the GREAT Britain and Northern Ireland Pavilions and linked locations across IBC2026 (Amsterdam RAI, 11 14 September)...

16/07/2026

Hitomi Broadcast to showcase HDR colour verification and...

Hitomi Broadcast will introduce Spectra, a new HDR colour verification solution measured in picture, not using VPID, at IBC2026 (Hall 10, Stand A40). Expanding ...