LPR Group

LPR Group

NVIDIA Learning and Perception Research Group

Welcome to the homepage of NVIDIA’s Learning and Perception Research group, led by Dr. Jan Kautz. Our research spans computer vision and machine learning. We are particularly interested in:

  • Human-centric Perception: body pose, hand pose, facial landmarks, gaze estimation, activity detection and recognition, etc.
  • Perception for Autonomous Machines: stereo, optical flow, object pose estimation, 3D shape estimation, etc.
  • Neural Content Capture and Synthesis: image and view synthesis, neural avatars, neural agents, denoising diffusion models, GANs, etc.
  • Resource-Efficient Deep Learning: pruning, NAS, efficient backbones, weakly- and self-supervised learning, etc.

Graduate students interested in interning with us are welcome reach out directly to team members for more details.

News

January 2024 - Happy New Year! Check out our three papers accepted for the International Conference on 3D Vision 2024, and our NeurIPS 2023 papers if you missed them!

April 2023 - Check out the publication page for a sneak peek of our papers accepted at CVPR (12 papers), ICRA (4 papers), and ICLR (2 papers)!!

December 2022 - We presented 7 papers at NeurIPS in New Orleans!

October 2022 - We’ll be presenting 7 papers at ECCV in Tel Aviv, come say hi!

September 2022 - The LPR website goes live!!

Members

Avatar

Jan Kautz

Team Leader

Avatar

Abhishek Badki

3D Vision, Deep Learning

Avatar

Ali Hatamizadeh

Computer Vision, Generative Learning

Avatar

Arash Vahdat

Generative Learning

Avatar

Ben Eckart

3D Vision

Avatar

Bowen Wen

3D Vision, Robotics

Avatar

Chao Liu

3D Vision, Inverse Problems

Avatar

Charles Loop

Real-time 3D Computer Graphics and Vision

Avatar

Christopher Choy

3D/4D Perception & Reconstruction, 3D Multi-Modal LLMs

Avatar

Daniel Leibovici

Scientific Computing, High Performance Computing

Avatar

De-An Huang

Video Understanding, Embodied AI

Avatar

Greg Heinrich

DL Model Architectures, DL Runtime Efficiency

Avatar

Hang Su

3D Vision, Deep Learning

Avatar

Hongxu (Danny) Yin

Efficient and Secure Deep Learning

Avatar

Iuri Frosio

Imaging, RL, Computational Aspects of DL

Avatar

Jean Kossaifi

Core ML

Avatar

Jeff Smith

3D Vision, Robotics

Avatar

Jim Fan

Robotics

Avatar

Jonathan Tremblay

Computer Vision, Robotics

Avatar

Kamyar Azizzadenesheli

ML, AI4Science, RL, Robotics, Operator Learning

Avatar

Karsten Kreis

Deep Generative Learning

Avatar

Morteza Mardani

Machine Learning, Generative Modeling, Inverse Problems

Avatar

Nikola B. Kovachki

Scientific Computing

Avatar

Orazio Gallo

Computer Vision, 3D Vision, Computational Photography

Avatar

Pavlo Molchanov

Machine Learning for CV

Avatar

Peter Belcak

Machine Learning

Avatar

Saurav Muralidharan

Efficient Deep Learning, Large Language Models

Avatar

Scott Reed

Robotics

Avatar

Sifei Liu

Computer Vision, Self-Supervised Learning

Avatar

Stan Birchfield

3D Vision, Robotics

Avatar

Stephen Tyree

Computer Vision, Robotics

Avatar

Thomas Breuel

Computer Vision

Avatar

Tomas Geffner

Probabilistic Machine Learning

Avatar

Umar Iqbal

Computer Vision, Digital Humans, Motion Capture

Avatar

Valts Blukis

Language Grounding, Robotics, 3D Vision

Avatar

Weili Nie

Generative Learning

Avatar

Wonmin Byeon

Spatio-Temporal Learning, Continual Learning

Avatar

Xiaolong Wang

Computer Vision

Avatar

Xueting Li

Computer Vision, 3D Vision

Avatar

Ye Yuan

3D Vision, Embodied AI, Reinforcement Learning

Avatar

Yuke Zhu

Embodied AI, Robotics, Foundation Models

Avatar

Zhenjia Xu

Robotics

Avatar

Zhiding Yu

Computer Vision, Visual Recognition, Representation Learning

Publications

Quickly discover relevant content by filtering publications.

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects