2026 Tero Karras: Computer Science Researcher – H-Index, Publications & Awards

Discipline name	D-Index	World Ranking	Current World Ranking	National Ranking	Current National Ranking	Publications	Citations
Computer Science	39	9456	9183	590	582	84	31153

Overview

Tero Karras is a researcher affiliated with Nvidia in the United Kingdom. Their academic work primarily spans the field of Computer Science, with a focus on computer vision and computer graphics. The subfields covered in their publications include Computer Vision and Pattern Recognition, Computer Graphics and Computer-Aided Design, Computational Mechanics, Radiology, Nuclear Medicine and Imaging, and General Health Professions.

The research topics associated with Tero Karras encompass:

Generative Adversarial Networks and Image Synthesis
Advanced Vision and Imaging
Computer Graphics and Visualization Techniques
3D Shape Modeling and Analysis
Digital Media Forensic Detection
Advanced Image Processing Techniques
Human Pose and Action Recognition

Tero Karras has contributed to multiple publication venues throughout their career. Frequent venues include:

arXiv (Cornell University)
Aaltodoc (Aalto University)
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
ACM Transactions on Graphics

Their recent publications reflect ongoing work in generative models and computer vision:

"Training Generative Adversarial Networks with Limited Data," 2020, arXiv (Cornell University)
"Efficient Geometry-aware 3D Generative Adversarial Networks," 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
"Alias-Free Generative Adversarial Networks," 2021, arXiv (Cornell University)
"Elucidating the Design Space of Diffusion-Based Generative Models," 2022, arXiv (Cornell University)
"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers," 2022, arXiv (Cornell University)

Tero Karras has collaborated frequently with several co-authors, including:

Timo Aila
Miika Aittala
Samuli Laine
Jaakko Lehtinen
Janne Hellsten

Best Publications

A Style-Based Generator Architecture for Generative Adversarial Networks

Tero Karras;Samuli Laine;Timo Aila

7855
Citations
Analyzing and Improving the Image Quality of StyleGAN

Tero Karras;Samuli Laine;Miika Aittala;Janne Hellsten

4884
Citations
Progressive Growing of GANs for Improved Quality, Stability, and Variation

Tero Karras;Timo Aila;Samuli Laine;Jaakko Lehtinen

4220
Citations
Efficient Geometry-aware 3D Generative Adversarial Networks

Unknown

1574
Citations
Pruning Convolutional Neural Networks for Resource Efficient Inference

Pavlo Molchanov;Stephen Tyree;Tero Karras;Timo Aila

1486
Citations
A Style-Based Generator Architecture for Generative Adversarial Networks

Tero Karras;Samuli Laine;Timo Aila

1387
Citations
Noise2Noise: Learning image restoration without clean data

Jaakko Lehtinen;Jaakko Lehtinen;Jacob Munkberg;Jon Hasselgren;Samuli Laine

1309
Citations
Training Generative Adversarial Networks with Limited Data

Tero Karras;Miika Aittala;Janne Hellsten;Samuli Laine

1055
Citations
Elucidating the Design Space of Diffusion-Based Generative Models

Unknown

845
Citations
Alias-Free Generative Adversarial Networks

Tero Karras;Miika Aittala;Samuli Laine;Erik Härkönen

797
Citations
Few-Shot Unsupervised Image-to-Image Translation

Ming-Yu Liu;Xun Huang;Arun Mallya;Tero Karras

682
Citations
Audio-driven facial animation by joint end-to-end learning of pose and emotion

Tero Karras;Timo Aila;Samuli Laine;Antti Herva

433
Citations
Efficient Sparse Voxel Octrees

S Laine;T Karras

356
Citations
Improved Precision and Recall Metric for Assessing Generative Models

Tuomas Kynkäänniemi;Tero Karras;Samuli Laine;Jaakko Lehtinen

320
Citations
Pruning Convolutional Neural Networks for Resource Efficient Transfer Learning.

Pavlo Molchanov;Stephen Tyree;Tero Karras;Timo Aila

317
Citations
Modular primitives for high-performance differentiable rendering

Samuli Laine;Janne Hellsten;Tero Karras;Yeongho Seol

261
Citations
Maximizing parallelism in the construction of BVHs, octrees, and k-d trees

Tero Karras

225
Citations
Fast parallel construction of high-quality bounding volume hierarchies

Tero Karras;Timo Aila

161
Citations
Efficient sparse voxel octrees

Samuli Laine;Tero Karras

146
Citations
High-Quality Self-Supervised Deep Image Denoising

Samuli Laine;Tero Karras;Jaakko Lehtinen;Timo Aila

144
Citations
Megakernels considered harmful: wavefront path tracing on GPUs

Samuli Laine;Tero Karras;Timo Aila

132
Citations
Architecture considerations for tracing incoherent rays

Timo Aila;Tero Karras

112
Citations

Frequent Co-Authors

Samuli Laine Nvidia (United States)

Timo Aila Aalto University

Jaakko Lehtinen Aalto University

Jan Kautz Nvidia (United States)

Ming-Yu Liu Nvidia (United States)

David Luebke Nvidia (United States)

Alexander Keller Nvidia (United States)

Anima Anandkumar Nvidia (United Kingdom)

Animesh Garg University of Toronto

Hao Li University of California, Berkeley

External Links

Personal website of Tero Karras

If you think any of the details on this page are incorrect, let us know.

Related Online Degrees & Career Pathways

For students considering a Computer Science degree in the USA, there are several related online programs and career pathways worth exploring. Many universities now offer accelerated cs degree options, allowing motivated learners to complete their studies faster and enter the workforce sooner.

Some may also be interested in fields closely related to technology, such as engineering and physics. Programs like environmental engineering schools online provide training in sustainability and environmental solutions, while mechanical engineering cost of education outlines affordable pathways to a career in engineering design and manufacturing.

For those leaning towards fundamental sciences, an online bachelor's degree in physics may be an ideal alternative or complement to computer science. Each of these degrees opens doors to a variety of high-demand tech, engineering, and research careers, with flexible online study making them more accessible than ever.