People

Tero Karras

Tero Karras works as a Distinguished Research Scientist at NVIDIA Research, which he joined in 2009. His current research interests revolve around deep learning, generative models, and digital content creation. He is the primary author of the StyleGAN family of generative models and has also had a pivotal role in the development of NVIDIA's RTX technology, including both hardware and software design.

Research Area(s)
Computer Graphics
Generative AI
Real-Time Rendering
Main Field of Interest
Artificial Intelligence and Machine Learning
Google Scholar
https://scholar.google.fi/citations?user=-50qJW8AAAAJ

Publications

2023

GeNVS: Generative Novel View Synthesis with 3D-Aware Diffusion Models
Eric R. Chan, Koki Nagano, Matthew Chan, Alexander W. Bergman, Jeong Joon Park, Axel Levy, Miika Aittala, Shalini De Mello, Tero Karras, Gordon Wetzstein
ICCV 2023

2022

Elucidating the Design Space of Diffusion-Based Generative Models
Tero Karras, Miika Aittala, Timo Aila, Samuli Laine
NeurIPS 2022 (oral)
NeurIPS Outstanding Paper
Efficient Geometry-aware 3D Generative Adversarial Networks
Eric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano, Boxiao Pan, Shalini De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, Gordon Wetzstein
IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2022
Oral presentation

2021

Alias-Free Generative Adversarial Networks
Tero Karras, Miika Aittala, Samuli Laine, Erik Härkönen, Janne Hellsten, Jaakko Lehtinen, Timo Aila
NeurIPS 2021

2020

Training Generative Adversarial Networks with Limited Data
Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, Timo Aila
NeurIPS 2020
Modular Primitives for High-Performance Differentiable Rendering
Samuli Laine, Janne Hellsten, Tero Karras, Yeongho Seol, Jaakko Lehtinen, Timo Aila
ACM Transactions on Graphics 39(6) (Proc. SIGGRAPH Asia 2020)
Semi-Supervised StyleGAN for Disentanglement Learning
Weili Nie, Tero Karras, Animesh Garg, Shoubhik Debnath, Anjul Patney, Ankit B. Patel, Anima Anandkumar
International Conference on Machine Learning (ICML) 2020
Analyzing and Improving the Image Quality of StyleGAN
Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, Timo Aila
CVPR 2020

2019

High-Quality Self-Supervised Deep Image Denoising
Samuli Laine, Tero Karras, Jaakko Lehtinen, Timo Aila
NeurIPS 2019
Improved Precision and Recall Metric for Assessing Generative Models
Tuomas Kynkäänniemi, Tero Karras, Samuli Laine, Jaakko Lehtinen, Timo Aila
NeurIPS 2019
Few-Shot Unsupervised Image-to-Image Translation
Ming-Yu Liu, Xun Huang, Arun Mallya, Tero Karras, Timo Aila, Jaakko Lehtinen, Jan Kautz
ICCV
A Style-Based Generator Architecture for Generative Adversarial Networks
Tero Karras, Samuli Laine, Timo Aila
IEEE CVPR 2019
Texture Level of Detail Strategies for Real-Time Ray Tracing
Tomas Akenine-Möller, Jim Nilsson, Magnus Andersson, Colin Barré-Brisebois, Robert Toth, Tero Karras
Ray Tracing Gems

2018

Noise2Noise: Learning Image Restoration without Clean Data
Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Samuli Laine, Tero Karras, Miika Aittala, Timo Aila
Proc. ICML 2018
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Tero Karras, Timo Aila, Samuli Laine, Jaakko Lehtinen
ICLR 2018

2017

Audio-Driven Facial Animation by Joint End-to-End Learning of Pose and Emotion
Tero Karras, Timo Aila, Samuli Laine, Antti Herva, Jaakko Lehtinen
SIGGRAPH 2017
Efficient Incoherent Ray Traversal on GPUs Through Compressed Wide BVHs
Henri Ylitie, Tero Karras, Samuli Laine
High-Performance Graphics 2017
Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks
Samuli Laine, Tero Karras, Timo Aila, Antti Herva, Shunsuke Saito, Ronald Yu, Hao Li, Jaakko Lehtinen
Symposium on Computer Animation 2017
Pruning Convolutional Neural Networks for Resource Efficient Inference
Pavlo Molchanov, Stephen Tyree, Tero Karras, Timo Aila, Jan Kautz
International Conference on Learning Representations (ICLR 2017)

2015

Apex Point Map for Constant-Time Bounding Plane Approximation
Samuli Laine, Tero Karras
Eurographics Symposium on Rendering 2015

2013

On Quality Metrics of Bounding Volume Hierarchies
Timo Aila, Tero Karras, Samuli Laine
Proc. High-Performance Graphics
Megakernels Considered Harmful: Wavefront Path Tracing on GPUs
Samuli Laine, Tero Karras, Timo Aila
High-Performance Graphics 2013
Fast Parallel Construction of High-Quality Bounding Volume Hierarchies
Tero Karras, Timo Aila
High Performance Graphics 2013
Gradient-Domain Metropolis Light Transport
Jaakko Lehtinen, Tero Karras, Samuli Laine, Miika Aittala, Frédo Durand, Timo Aila
ACM Transactions on Graphics (Proc. SIGGRAPH 2013)

2012

Maximizing Parallelism in the Construction of BVHs, Octrees, and k-d Trees
Tero Karras
High Performance Graphics 2012
Understanding the Efficiency of Ray Traversal on GPUs - Kepler and Fermi Addendum
Timo Aila, Samuli Laine, Tero Karras
NVIDIA Technical Report NVR-2012-002

2011

Improved Dual-Space Bounds for Simultaneous Motion and Defocus Blur
Samuli Laine, Tero Karras
NVIDIA Technical Report NVR-2010-004
Efficient Triangle Coverage Tests for Stochastic Rasterization
Samuli Laine, Tero Karras
NVIDIA Technical Report NVR-2010-003
High-Performance Software Rasterization on GPUs
Samuli Laine, Tero Karras
High-Performance Graphics 2011
Clipless Dual-Space Bounds for Faster Stochastic Rasterization
Samuli Laine, Timo Aila, Tero Karras, Jaakko Lehtinen
ACM Transactions in Graphics 30(4) (Proc. SIGGRAPH 2011)
Stratified Sampling for Stochastic Transparency
Samuli Laine, Tero Karras
Computer Graphics Forum 30(4) (EGSR 2011)

2010

Architecture Considerations for Tracing Incoherent Rays
Timo Aila, Tero Karras
Proc. High-Performance Graphics 2010
Two Methods for Fast Ray-Cast Ambient Occlusion
Samuli Laine, Tero Karras
Eurographics Symposium on Rendering 2010
Efficient Sparse Voxel Octrees
Samuli Laine, Tero Karras
ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D)
Efficient Sparse Voxel Octrees - Analysis, Extensions, and Implementation
Samuli Laine, Tero Karras
NVIDIA Technical Report NVR-2010-001