This site requires Javascript in order to view all its content. Please enable Javascript in order to access all the functionality of this web site. Here are the instructions how to enable JavaScript in your web browser.

NVIDIA at ICCV 2021

Connect with NVIDIA researchers at this year’s online International Conference on Computer Vision (ICCV) to learn more about the amazing work we're doing. Come see how NVIDIA researchers are collaborating with ICCV members to deliver AI breakthroughs across the community.

It all happens October 11–17, 2021.

Schedule at a Glance

NVIDIA researchers will present 14 papers at ICCV that feature a range of groundbreaking research in the field of computer vision. From unsupervised 3D neural rendering of gaming worlds to physics-based human motion estimation and synthesis from videos, explore the work NVIDIA is bringing to the ICCV community.

Monday 10/11	Tuesday 10/12	Wednesday 10/13	Thursday 10/14	Friday 10/15
		Self-Supervised Object Detection via Generative Image Synthesis \| Session 7A \| 8:00–9:00 a.m. EDT	Video Matting via Consistency-Regularized Graph Neural Networks \| Session 4B \| 8:00–9:00 a.m. EDT
		Active Learning for Deep Object Detection via Probabilistic Modeling \| Session 8A \| 9:00–10:00 a.m. EDT	Deep Permutation Equivariant Structure from Motion \| Session 5B \| 9:00–10:00 a.m. EDT
		Video Autoencoder: Self-Supervised Disentanglement of 3D Structure and Motion \| Session 8A \| 9:00–10:00 a.m. EDT	Self-Calibrating Neural Radiance Field \| Session 5B \| 9:00–10:00 a.m. EDT
		Physics-Based Human Motion Estimation and Synthesis from Videos \| Session 9A \| 10:00–11:00 a.m. EDT		Learning Indoor Reverse Rendering with 3D Spatially Varying Lighting \| Session 10B \| 10:00–11:00 a.m. EDT
				3DStyleNet: Creating 3D Shapes with Geometrics and Texture Style Variations \| Session 10B \| 10:00–11:00 a.m. EDT
				GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds \| Session 11B \| 11:00 a.m.–12:00 p.m. EDT
Differentiable 3D Vision and Graphics \| Half day, afternoon \| Workshop	T-AutoML: Automated Machine Learning for Lesion Segmentation Using Transformers in 3D Medical Imaging \| Session 3A \| 12:00–1:00 p.m. EDT			The Second Learning for Computational Imaging (LCI) Workshop: Sensing, Reconstruction, and Analysis \| Half day, afternoon \| Workshop
	DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision \| Session 3A \| 12:00–1:00 p.m. EDT			Self-Supervised Real-to-Sim Scene Generation \| Session 12B \| 12:00–1:00 p.m. EDT
	Video Matting via Consistency-Regularized Graph Neural Networks \| Session 4A \| 3:00–4:00 p.m. EDT
	Deep Permutation Equivariant Structure from Motion \| Session 5A \| 4:00–5:00 p.m. EDT			Self-Supervised Object Detection via Generative Image Synthesis \| Session 7B \| 4:00–5:00 p.m. EDT
	Self-Calibrating Neural Radiance Fiel \| Session 5A \| 4:00–5:00 p.m. EDT
				Active Learning for Deep Object Detection via Probabilistic Modeling \| Session 8B \| 5:00–6:00 p.m. EDT
				Video Autoencoder: Self-Supervised Disentanglement of 3D Structure and Motion \| Session 8B \| 5:00–6:00 p.m. EDT
				Physics-Based Human Motion Estimation and Synthesis from Videos \| Session 9B \| 5:00–6:00 p.m. EDT
		Learning Indoor Reverse Rendering with 3D Spatially Varying Lighting \| Session 10A \| 6:00–7:00 p.m. EDT
		3DStyleNet: Creating 3D Shapes with Geometrics and Texture Style Variations \| Session 10A \| 6:00–7:00 p.m. EDT
		GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds \| Session 11A \| 7:00–8:00 p.m. EDT	T-AutoML: Automated Machine Learning for Lesion Segmentation Using Transformers in 3D Medical Imaging \| Session 3B \| 7:00–8:00 p.m. EDT
		Self-Supervised Real-to-Sim Scene Generation \| Session 12A \| 8:00– 9:00 p.m. EDT

Enter our drawing for a chance to win an NVIDIA GPU.

ENTER NOW

Featured Demos

GANverse3D: Knight Rider’s KITT Re-created with AI by NVIDIA

NVIDIA GANverse3D is a powerful breakthrough for 2D-to-3D models. Now, it's possible to create a 3D, animatable model with a single 2D picture.

WATCH NOW ›

One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

Learn how this AI technology can be used for video conferencing, story telling, virtual assistants, and more.

WATCH NOW ›

NVIDIA NGC Catalog

Collections from the NVIDIA NGC™ catalog are use-case-based content. They’re curated in easy-to-use packages that make it easy to discover the compatible framework containers, models, Jupyter notebooks, detailed documentation, and other resources to get you started faster with your AI use cases.

WATCH NOW ›

NVIDIA Maxine

NVIDIA Maxine™ is a GPU-accelerated SDK with state-of-the-art AI features for developers to build virtual collaboration and content creation applications such as video conferencing and live streaming.

WATCH NOW ›

Trainings & Resources

NVIDIA Developer Program

Get the advanced tools and training you need to successfully build applications on all NVIDIA technology platforms.

LEARN MORE ›

Unlock Your Startup’s Potential

NVIDIA Inception nurtures cutting-edge technology startups that are revolutionizing industries. The program offers go-to-market support, expertise, and technology—all tailored to a business’s evolution, no matter what size or funding stage they’re at.

JOIN NOW ›

NVIDIA Applied Research Accelerator Program

The NVIDIA Applied Research Accelerator Program supports research projects that have the potential to make a real-world impact through deployment into GPU-accelerated applications adopted by commercial and government organizations.

LEARN MORE ›

Accelerate 3D Deep Learning Research with Kaolin and Omniverse Kaolin App

The NVIDIA Omniverse™ Kaolin app is a powerful visualization tool that simplifies and accelerates 3D deep learning research using NVIDIA’s Kaolin PyTorch library. The Kaolin app leverages the Omniverse platform, Universal Scene Description (USD) format, and NVIDIA RTX™ rendering to visualize 3D outputs of any deep learning model as it’s training, Kaolin inspects 3D datasets to find inconsistencies and gain intuition and render large synthetic datasets from collections of 3D data.

WATCH THE OVERVIEW ›

Connecting in the Metaverse: The Making of the GTC Keynote

Get a behind-the-scenes look at how a small team of NVIDIA researchers, artists, and engineers used NVIDIA Omniverse, an open platform for virtual collaboration and real-time physically accurate simulation, to blur the line between real and rendered.

WATCH NOW ›

Like No Place You’ve Ever Worked

At NVIDIA, you’ll solve some of the world’s hardest problems and discover never-before-seen ways to improve the quality of life for people everywhere. From healthcare to robots, self-driving cars to blockbuster movies—and a growing list of new opportunities every single day. Explore all of our open roles, including internships and new college graduate positions.

Learn more about our career opportunities by exploring current job openings as well as university jobs.

LEARN MORE

Brilliant Minds. Breakthrough Discoveries.

Join the conference for AI innovators, technologists, and creators.

Monday 10/11	Tuesday 10/12	Wednesday 10/13	Thursday 10/14	Friday 10/15
		Self-Supervised Object Detection via Generative Image Synthesis \| Session 7A \| 8:00–9:00 a.m. EDT	Video Matting via Consistency-Regularized Graph Neural Networks \| Session 4B \| 8:00–9:00 a.m. EDT
		Active Learning for Deep Object Detection via Probabilistic Modeling \| Session 8A \| 9:00–10:00 a.m. EDT	Deep Permutation Equivariant Structure from Motion \| Session 5B \| 9:00–10:00 a.m. EDT
		Video Autoencoder: Self-Supervised Disentanglement of 3D Structure and Motion \| Session 8A \| 9:00–10:00 a.m. EDT	Self-Calibrating Neural Radiance Field \| Session 5B \| 9:00–10:00 a.m. EDT
		Physics-Based Human Motion Estimation and Synthesis from Videos \| Session 9A \| 10:00–11:00 a.m. EDT		Learning Indoor Reverse Rendering with 3D Spatially Varying Lighting \| Session 10B \| 10:00–11:00 a.m. EDT
				3DStyleNet: Creating 3D Shapes with Geometrics and Texture Style Variations \| Session 10B \| 10:00–11:00 a.m. EDT
				GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds \| Session 11B \| 11:00 a.m.–12:00 p.m. EDT
Differentiable 3D Vision and Graphics \| Half day, afternoon \| Workshop	T-AutoML: Automated Machine Learning for Lesion Segmentation Using Transformers in 3D Medical Imaging \| Session 3A \| 12:00–1:00 p.m. EDT			The Second Learning for Computational Imaging (LCI) Workshop: Sensing, Reconstruction, and Analysis \| Half day, afternoon \| Workshop
	DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision \| Session 3A \| 12:00–1:00 p.m. EDT			Self-Supervised Real-to-Sim Scene Generation \| Session 12B \| 12:00–1:00 p.m. EDT
	Video Matting via Consistency-Regularized Graph Neural Networks \| Session 4A \| 3:00–4:00 p.m. EDT
	Deep Permutation Equivariant Structure from Motion \| Session 5A \| 4:00–5:00 p.m. EDT			Self-Supervised Object Detection via Generative Image Synthesis \| Session 7B \| 4:00–5:00 p.m. EDT
	Self-Calibrating Neural Radiance Fiel \| Session 5A \| 4:00–5:00 p.m. EDT
				Active Learning for Deep Object Detection via Probabilistic Modeling \| Session 8B \| 5:00–6:00 p.m. EDT
				Video Autoencoder: Self-Supervised Disentanglement of 3D Structure and Motion \| Session 8B \| 5:00–6:00 p.m. EDT
				Physics-Based Human Motion Estimation and Synthesis from Videos \| Session 9B \| 5:00–6:00 p.m. EDT
		Learning Indoor Reverse Rendering with 3D Spatially Varying Lighting \| Session 10A \| 6:00–7:00 p.m. EDT
		3DStyleNet: Creating 3D Shapes with Geometrics and Texture Style Variations \| Session 10A \| 6:00–7:00 p.m. EDT
		GANcraft: Unsupervised 3D Neural Rendering of Minecraft Worlds \| Session 11A \| 7:00–8:00 p.m. EDT	T-AutoML: Automated Machine Learning for Lesion Segmentation Using Transformers in 3D Medical Imaging \| Session 3B \| 7:00–8:00 p.m. EDT
		Self-Supervised Real-to-Sim Scene Generation \| Session 12A \| 8:00– 9:00 p.m. EDT

NVIDIA at ICCV 2021

Schedule at a Glance

Enter our drawing for a chance to win an NVIDIA GPU.

Featured Demos

GANverse3D: Knight Rider’s KITT Re-created with AI by NVIDIA

One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing

NVIDIA NGC Catalog

NVIDIA Maxine​

Trainings & Resources

NVIDIA Developer Program

Unlock Your Startup’s Potential

NVIDIA Applied Research Accelerator Program

Accelerate 3D Deep Learning Research with Kaolin and Omniverse Kaolin App

Connecting in the Metaverse: The Making of the GTC Keynote

Like No Place You’ve Ever Worked

Brilliant Minds. Breakthrough Discoveries.

NVIDIA Maxine