NVIDIA at CVPR 2023

June 18–22, 2023

NVIDIA Research Papers
Deep Dive
Featured Demos
Careers

NVIDIA Research Papers
Deep Dive
Featured Demos
Careers

Connect with NVIDIA researchers at this year’s Computer Vision and Pattern Recognition (CVPR) online conference and learn more about the work we’ll be presenting—including forty eight papers. Come see how NVIDIA Research collaborates with CVPR members to deliver AI breakthroughs across the community.

It all happens June 18–22, 2023.

NVIDIA Research Papers at CVPR 2023

NVIDIA’s accepted papers at this year’s online CVPR feature a range of groundbreaking research in the field of computer vision. From human motion forecasting to extracting triangular 3D models, materials, and lighting from images, explore the work NVIDIA is bringing to the CVPR community.

* Denotes equal contribution to the paper.

Magic3D: High-Resolution Text-to-3D Content Creation

Chen-Hsuan Lin*, Jun Gao*, Luming Tang*, Towaki Takikawa*, Xiaohui Zeng*, Xun Huang, Karsten Kreis, Sanja Fidler*, Ming-Yu Liu*, Tsung-Yi Lin | Coming Soon

Align Your Latents: High-Resolution Video Synthesis With Latent Diffusion Models

Andreas Blattmann*, Robin Rombach*, Huan Ling*, Tim Dockhorn, Seung Wook Kim, Sanja Fidler, Karsten Kreis | Coming Soon

Neural Kernel Surface Reconstruction

Jiahui Huang, Zan Gojcic, Matan Atzmon, Or Litany, Sanja Fidler, Francis Williams | Coming Soon

Affordance Diffusion: Synthesizing Hand-Object Interactions

Yufei Ye, Xueting Li, Abhinav Gupta, Shalini De Mello, Stan Birchfield, Jiaming Song, Shubham Tulsiani, Sifei Liu | Coming Soon

Neuralangelo: High-Fidelity Neural Surface Reconstruction

Zhaoshuo Li, Thomas Muller, Alex Evans, Russell H. Taylor, Mathias Unberath, Ming-Yu Liu, Chen-Hsuan Lin | Coming Soon

Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters

Jiashun Wang, Xueting Li, Sifei Liu, Shalini De Mello, Orazio Gallo, Xiaolong Wang, Jan Kautz | Coming Soon

The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks

Luri Frosio, Jan Kautz | Coming Soon

DiffCollage: Parallel Generation of Large Content With Diffusion Models

Qinsheng Zhang, Jiaming Song, Xun Huang, Yongxin Chen, Ming-Yu Liu | Coming Soon

FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

Jiawei Yang, Marco Pavone, and Yue Wang | Coming Soon

Vision Transformers are Good Mask Auto-Labelers

Shiyi Lan, Xitong Yang, Zhiding Yu, Zuxuan Wu, Jose M. Alvarez, Anima Anandkumar | Coming Soon

VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion

SYiming Li, Zhiding Yu, Chris Choy, Chaowei Xiao, Jose M. Alvarez, Sanja Fidler, Chen Feng, Anima Anandkumar | Coming Soon

Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models

Jiarui Xu, Sifei Liu, Arash Vahdat, Wonmin Byeon, Xiaolong Wang, Shalini De Mello | Coming Soon

GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields

Alessandro Ruzzi, Xiangwei Shi, Xi Wang, Gengyan Li, Shalini De Mello, Hyung Jin Chang, Xucong Zhang, Otmar Hilliges | Coming Soon

Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion

Davis Rempe, Zhengyi Luo, Xue Bin Peng, Ye Yuan, Kris M. Kitani, Karsten Kreis, Sanja Fidler, Or Litany | Coming Soon

Heterogeneous Continual Learning

Divyam Madaan, Hongxu Yin, Wonmin Byeon, Jan Kautz, Pavlo Molchanov | Coming Soon

Global Vision Transformer Pruning With Hessian-Aware Saliency

Huanrui Yang, Hongxu Yin, Maying Shen, Pavlo Molchanov, Hai Li, Jan Kautz | Coming Soon

Recurrence Without Recurrence: Stable Video Landmark Detection With Deep Equilibrium Models

Paul Micaelli, Pavlo Molchanov, Arash Vahdat, Hongxu Yin, Jan Kautz | Coming Soon

Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids

Wei Dong, Chris Choy, Charles Loop, Or Litany, Yuke Zhu | Coming Soon

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

Taeyeop Lee, Jonathan Tremblay, Valts Blukis, Bowen Wen, Byeong-Uk Lee, Inkyu Shin, Stan Birchfield, In So Kweon, Kuk-Jin Yoon | Coming Soon

NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models

Seung Wook Kim*, Bradley Brown*, Kangxue Yin, Karsten Kreis, Katja Schwarz, Daiqing Li, Robin Rombach, Antonio Torralba, Sanja Fidler | Coming Soon

Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes

Zian Wang, Tianchang Shen, Jun Gao, Shengyu Huang, Jacob Munkberg, Jon Hasselgren, Zan Gojcic, Wenzheng Chen, Sanja Fidler | Coming Soon

Learning 3D Reconstruction Network From 2D StyleGAN

Aysegul Dundar, Jun Gao, Andrew Tao, Bryan Catanzaro | Coming Soon

Learning Human-to-Robot Handovers From Point Clouds

Sammy Christen, Wei Yang, Claudia Pérez-D'Arpino, Otmar Hilliges, Dieter Fox, Yu-Wei Chao | Coming Soon

Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Bowen Wen, Jonathan Tremblay, Valts Blukis, Stephen Tyree, Thomas Müller, Alex Evans, Dieter Fox, Jan Kautz, Stan Birchfield | Coming Soon

Load Less

Deep Dive

Accelerating Digital Pathology Workflows Using cuCIM and NVIDIA GPUDirect Storage

cuCIM with NVIDIA® GPUDirect® Storage (GDS) accelerates runtimes by up to 2X. Learn how writing image data directly to GPU memory can reduce input and output (IO) times for high-resolution images.

Read About It Here

Image courtesy of Microsoft Bing

Increasing Throughput and Reducing Cost for AI-Based Computer Vision With CV-CUDA

CV-CUDA® open beta optimizes pre- and postprocessing for an end-to-end throughput improvement of up to 49X over OpenCV CPU. CV-CUDA enables real-time, high-performance, cloud-scale applications that demand lower latency and higher throughput.

Learn More on CV-CUDA

Deep Imagination Research

NVIDIA Deep Imagination Research Group consists of a group of researchers passionate about deep generative models and their applications in content creation.

Explore the Lab

NVIDIA Instant NeRF

NVIDIA Instant NeRF is software that uses AI and neural radiance fields (NeRF) to approximate how light behaves in the real world, enabling users to reconstruct a 3D scene from a handful of images taken at different angles in a matter of seconds.

Grab the Code

Featured Demos

Explore how NVIDIA technologies are transforming a variety of industries with powerful demos that highlight the latest breakthroughs in AI, data science, graphics, healthcare, and more.

View All

NVIDIA Picasso Service

Explore Picasso, a cloud-based generative AI solution for creating images, videos, and 3D applications.

Watch Now

CV-CUDA

See how Runway is optimizing AI image and video generation tools using CV-CUDA.

Watch Now

NVIDIA NeMo Service

Learn how NVIDIA NeMo™ service can boost enterprise productivity with customized generative AI models.

Watch Now

NVIDIA Omniverse

Check out the GTC Spring 2023 montage of NVIDIA Omniverse™ foundational technology in action.

Watch Now

NVIDIA Research AI Playground

Discover our most recent AI research and the new capabilities deep learning brings to visual and audio applications. Explore the latest innovations and see how you can bring them into your own work.

Play Here

Resources

NVIDIA Developer Program

Join our free Developer Program to access the 600+ SDKs, AI models, community forums, tech blogs, and technical resources that can accelerate your work and advance your skills.

Join Today

NVIDIA Deep Learning Institute

Upgrade your technical expertise, develop practical skills, and earn certificates showing subject matter competency with self-paced courses and instructor-led, hands-on workshops.

Learn More

NVIDIA Inception for Startups

Explore the program that provides cutting-edge startups around the world with critical access to go-to-market support, technical expertise, training, and funding opportunities.

Learn More

Meet Inception Startups Working in Computer Vision

NVIDIA Inception is helping over 14,000 startups worldwide faster, including many working in the field of computer vision. Explore some of our members.

Datagen

Dataminr

Deci AI

Encord

iniVation

Jabbr

Keylabs.AI

Kolena Inc

Labelbox

Lightning AI

Manot

Novarc Technologies

Nuvilabs

Rendered AI

Scale AI

SKY ENGINE AI

SkyLab

Spleenlab GMBH

SuperAnnotate

Synthesis AI

Synthetaic

TANgram VisiON

Tensorleap

Weights and Biases

Like No Place You’ve Ever Worked

Working 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, you’ll experience it all. Plus, there’s 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 current job openings, as well as university jobs.

Learn More

NVIDIA at CVPR 2023

NVIDIA Research Papers at CVPR 2023

Magic3D: High-Resolution Text-to-3D Content Creation

Align Your Latents: High-Resolution Video Synthesis With Latent Diffusion Models

Neural Kernel Surface Reconstruction

Affordance Diffusion: Synthesizing Hand-Object Interactions

Neuralangelo: High-Fidelity Neural Surface Reconstruction

Zero-Shot Pose Transfer for Unrigged Stylized 3D Characters

The Best Defense Is a Good Offense: Adversarial Augmentation Against Adversarial Attacks

DiffCollage: Parallel Generation of Large Content With Diffusion Models

FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularization

Vision Transformers are Good Mask Auto-Labelers

VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion

Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models

GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields

Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion

Heterogeneous Continual Learning

Global Vision Transformer Pruning With Hessian-Aware Saliency

Recurrence Without Recurrence: Stable Video Landmark Detection With Deep Equilibrium Models

Fast Monocular Scene Reconstruction With Global-Sparse Local-Dense Grids

TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation

NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models

Neural Fields Meet Explicit Geometric Representations for Inverse Rendering of Urban Scenes

Learning 3D Reconstruction Network From 2D StyleGAN

Learning Human-to-Robot Handovers From Point Clouds

Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects

Deep Dive

Accelerating Digital Pathology Workflows Using cuCIM and NVIDIA GPUDirect Storage

Increasing Throughput and Reducing Cost for AI-Based Computer Vision With CV-CUDA

Deep Imagination Research

NVIDIA Instant NeRF

Featured Demos

NVIDIA Picasso Service

CV-CUDA

NVIDIA NeMo Service

NVIDIA Omniverse

NVIDIA Research AI Playground

Resources

NVIDIA Developer Program

NVIDIA Deep Learning Institute

NVIDIA Inception for Startups

Meet Inception Startups Working in Computer Vision

Like No Place You’ve Ever Worked

Sign up to receive the latest news from NVIDIA.