Engage with NVIDIA researchers to learn more about the work we’ll be presenting at this year’s Computer Vision and Pattern Recognition (CVPR) online conference. NVIDIA researchers will present fifteen papers and posters on June 14–19, 2020.

NVIDIA research features AI breakthroughs with collaborations across the CVPR community.


NVIDIA’s accepted papers at this year’s online CVPR feature a range of groundbreaking research in the field of computer vision. From simulating dynamic gaming environments to powering coarse-to-fine neural architecture search for medical imaging, explore the work NVIDIA is bringing to the CVPR community.

Learning to Simulate Dynamic Environments With GameGAN

Seung Wook Kim  |  Yuhao Zhou  |  Jonah Philion  |  Antonio Torralba  |  Sanja Fidler  |  Paper  | CVPR Talk

Bi3D: Stereo Depth Estimation via Binary Classifications

Abhishek Badki | Alejandro Troccoli | Kihwan Kim | Jan Kautz | Pradeep Sen | Orazio Gallo  |  Paper | CVPR Talk

Meshlet Priors for 3D Mesh Reconstruction

Abhishek Badki | Orazio Gallo | Jan Kautz | Pradeep Sen  |  Paper  | CVPR Talk

Self-Supervised Viewpoint Learning From Image Collections

Siva Karthik Mustikovela | Varun Jampani | Shalini De Mello | Sifei Liu | Umar Iqbal | Carsten Rother | Jan Kautz |  Paper | CVPR Talk

Two-Shot Spatially Varying BRDF and Shape Estimation

Mark Boss | Varun Jampani | Kihwan Kim | Hendrik P.A. Lensch | Jan Kautz |  Paper  | CVPR Talk

C2FNAS: Coarse-to-Fine Neural Architecture Search for 3D Medical Image Segmentation

Qihang Yu | Dong Yang | Holger Roth | Yutong Bai | Yixiao Zhang | Alan L. Yuille | Daguang Xu |  Paper  |  CVPR Talk

Novel View Synthesis of Dynamic Scenes with Globally Coherent Depths fFrom a Monocular Camera

Jae Shin Yoon | Kihwan Kim | Orazio Gallo | Hyun Soo Park | Jan Kautz |  Paper  | CVPR Talk

Analyzing and Improving the Image Quality of StyleGAN

Tero Karras | Samuli Laine | Miika Aittala | Janne Hellsten | Jaakko Lehtinen | Timo Aila |  Paper  | CVPR Talk

Panoptic-Based Image Synthesis

Aysegul Dundar | Karan Sapra | Guilin Liu | Andrew Tao | Bryan Catanzaro |  Paper | CVPR Talk

Dreaming to Distill: Data-Free Knowledge Transfer via DeepInversion

Hongxu Yin | Pavlo Molchanov | Jose M. Alvarez | Zhizhong Li | Arun Mallya | Derek Hoiem | Niraj K. Jha | Jan Kautz |  PaperCVPR Talk

Instance-Aware, Context-Focused, and Memory-Efficient Weakly Supervised Object Detection

Zhongzheng Ren | Zhiding Yu | Xiaodong Yang | Ming-Yu Liu | Yong Jae Lee | Alexander G. Schwing | Jan Kautz  |  PaperCVPR Talk

UNAS: Differentiable Architecture Search Meets Reinforcement Learning

Arash Vahdat | Arun Mallya | Ming-Yu Liu | Jan Kautz |   PaperCVPR Talk

Workshops and Tutorials

Deep Dive

Jarvis Live Webinar | July 7

Learn how to build speech recognition, natural language understanding, and speech synthesis services with NVIDIA NeMo and Jarvis. First, we'll cover the basics of the NeMo toolkit for training and fine-tuning conversational AI models on your data. Then, we'll discuss how to use Jarvis to deploy and combine these services into a complete conversational AI solution.

Inside NVIDIA's Multi-Instance GPU Feature

NVIDIA's latest GPUs have an important new feature: Multi-Instance GPU (MIG). MIG allows large GPUs to be effectively divided into multiple instances of smaller GPUs. The primary benefit of the MIG feature is increasing GPU utilization by enabling the GPU to be efficiently shared by unrelated parallel compute workloads on bare metal, GPU pass-through, or on multiple vGPUs.

Watch an Autonomous Vehicle Navigate Around Silicon Valley

NVIDIA DRIVE Constellation enables high-fidelity, end-to-end simulation for development and validation of autonomous vehicles.

Misty: The Making of NVIDIA’s 3D AI Chatbot

Misty is NVIDIA’s take on a 3D animated, intelligent, interactive chatbot, brought to life in Omniverse. Misty connects our state of the art Jarvis conversational AI technology to our state of the art AI computer graphics technology.

Dramatic Gains in Performance and Utilization with Multi-Instance GPUs

Multi-Instance GPU (MIG) mode on the NVIDIA A100 Tensor Core GPU can guarantee performance for up to seven jobs running concurrently on the same GPU.

Synthesizing High-Resolution Images with GANs

Developed by NVIDIA researchers, StyleGAN2 yields state-of-the-art results in data-driven unconditional generative image modeling.

Protect Healthcare Data with Federated Learning

NVIDIA Clara Federated Learning is a reference application for distributed, collaborative AI model training that preserves patient privacy.

The Robotics Factory of the Future

NVIDIA Isaac Simis the industry’s first robotic AI development platform with simulation, navigation, and manipulation.

A Big Leap in AI Rendering

NVIDIA DLSS 2.0 is a DL-powered temporal video reconstruction algorithm that renders graphics at twice the speed of traditional techniques, with better image quality.

AI Inferencing at the Speed of Light

NVIDIA A100 GPUs deliver significantly faster performance for  image classification workloads.


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.

Explore current job openings as well as university jobs, or join us for a live session to meet with the managers.

Sign up to receive the latest news from NVIDIA.