PeopleofSuperintelligence

Researcher

Samuli Laine

Samuli Laine is a research scientist at NVIDIA whose work moved from GPU rendering to image-generating neural networks. He earned his M.Sc. and Ph.D. degrees from Helsinki University of Technology in 2006 and joined NVIDIA Research in 2007. With Tero Karras, Timo Aila and colleagues, he coauthored Progressive Growing of GANs in 2018 and A Style-Based Generator Architecture for Generative Adversarial Networks in 2019, which received a CVPR best paper honorary mention. The 2022 paper Elucidating the Design Space of Diffusion-Based Generative Models, written with Karras, Miika Aittala and Aila, won a NeurIPS Outstanding Paper award, and Guiding a Diffusion Model with a Bad Version of Itself was a best paper runner-up at NeurIPS 2024. He is a Distinguished Research Scientist at NVIDIA and a docent at Aalto University.

Works
107
Citations
33,729
h-index
39
Badges

Publication numbers from OpenAlex, as of 22 October 2026.

Timeline

  1. 2006

    Doctorate on shadow algorithms

    He receives M.Sc. and Ph.D. degrees in Information Technology from Helsinki University of Technology in 2006. His doctoral thesis, Efficient Physically-Based Shadow Algorithms, develops efficient algorithms for computing shadows in computer-generated images.

  2. 2007

    Joining NVIDIA Research

    He joins NVIDIA Research in 2007. His work there ranges from photorealistic and real-time rendering to voxel-based graphics, GPU ray tracing and 3D content creation.

  3. 2013

    Wavefront path tracing on GPUs

    With Tero Karras and Timo Aila, he coauthors Megakernels Considered Harmful: Wavefront Path Tracing on GPUs at High-Performance Graphics in 2013. The paper implements a path tracer on a GPU in a wavefront formulation.

  4. 2017–2018

    Face capture and Noise2Noise

    In 2017, he coauthors Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks, a real-time deep learning framework that tracks an actor's face in 3D from monocular video. In 2018, he coauthors Noise2Noise with Jaakko Lehtinen, Tero Karras, Timo Aila and others, which shows that images can be restored by learning from corrupted examples alone.

  5. 2018–2020

    Progressive GANs and StyleGAN

    In 2018, he coauthors Progressive Growing of GANs for Improved Quality, Stability, and Variation with Tero Karras, Timo Aila and Jaakko Lehtinen, which grows the generator and discriminator step by step from a low resolution. A Style-Based Generator Architecture for Generative Adversarial Networks, written with Karras and Aila, receives a best paper honorary mention at CVPR 2019, and the 2020 follow-up is Analyzing and Improving the Image Quality of StyleGAN.

  6. 2022

    NeurIPS Outstanding Paper award

    In 2022, he coauthors Elucidating the Design Space of Diffusion-Based Generative Models with Tero Karras, Miika Aittala and Timo Aila. The paper presents a design space that separates the concrete design choices of diffusion models, and it is named an Outstanding Paper at NeurIPS 2022.

  7. 2024

    Guidance from a weaker model

    Guiding a Diffusion Model with a Bad Version of Itself, coauthored with Tero Karras, Miika Aittala, Tuomas Kynkäänniemi, Jaakko Lehtinen and Timo Aila, is a best paper runner-up at NeurIPS 2024. The method guides generation with a smaller, less-trained version of the model itself and sets record FIDs of 1.01 for 64x64 and 1.25 for 512x512 ImageNet generation.

  8. As of October 2026

    Distinguished scientist at NVIDIA

    He is a Distinguished Research Scientist at NVIDIA and a docent at Aalto University, with a focus on deep learning and its applications in computer graphics. In March 2026, he coauthors Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models with David McAllister, Miika Aittala, Tero Karras, Janne Hellsten, Angjoo Kanazawa and Timo Aila.

Career

  1. Since 2007NVIDIADistinguished Research Scientist
  2. NowAalto UniversityDocent

Education

  1. 2006Aalto UniversityM.Sc.

From the biography and OpenAlex affiliations (the years of papers that list the organization), so some years are approximate.

Most-cited works

  1. A Style-Based Generator Architecture for Generative Adversarial Networks2019 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 11,671 citationsWith Tero Karras
  2. Analyzing and Improving the Image Quality of StyleGAN2020 · IEEE Computer Society Conference on Computer Vision and Pattern Recognition · 6,312 citationsWith Miika Aittala and Tero Karras
  3. Progressive Growing of GANs for Improved Quality, Stability, and Variation2017 · 4,723 citationsWith Tero Karras
  4. Temporal Ensembling for Semi-Supervised Learning2016 · 1,910 citations
  5. Alias-Free Generative Adversarial Networks2021 · 1,169 citationsWith Miika Aittala and Tero Karras

From OpenAlex, as of 21 October 2026.

  1. Google has the highest combined h-index among AI organizationsIncludes NVIDIA. We estimate that Google holds the highest combined h-index at 8,016, while universities account for 73% of the deduplicated total across AI organizations.
  2. 20% of people at companies who shape AI also hold a university role, led by Google and Stanford UniversityIncludes NVIDIA. We estimate that 539 of the 6,766 people with a known current organization (8%) hold both a university role and a company role, including 20% of people at companies and 13% of people at universities.
  3. Google alumni have founded or led 133 other organizations, more than any other AI labIncludes NVIDIA. We estimate that alumni of 17 major AI labs went on to found or lead 350 other organizations, including 226 they founded, and we trace 472 career moves directly between 23 labs since 2010.
  4. Universities (31%) and startups and other companies (25%) employ the largest shares of 2020–2026 entrantsIncludes NVIDIA. Among 819 people whose first recorded role started in 2020–2026 and who have a known current organization, 60% work in commercial sectors (25% at startups and other companies, 23% at frontier labs and 13% at big tech, with 9 in two), and 31% work at universities, compared with 66% for earlier entrants.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Samuli Laine yet. Send us a free-licensed photo.

  1. Samuli Laine – ACM SIGGRAPH HISTORY ARCHIVES history.siggraph.org. Checked 20 October 2026.
  2. Samuli Laine - Homepage users.aalto.fi. Checked 20 October 2026.
  3. Samuli Laine | Research research.nvidia.com. Checked 20 October 2026.
  4. Noise2Noise: Learning Image Restoration without Clean Data arxiv.org. Checked 20 October 2026.
  5. Progressive Growing of GANs for Improved Quality, Stability, and Variation arxiv.org. Checked 20 October 2026.
  6. A Style-Based Generator Architecture for Generative Adversarial Networks arxiv.org. Checked 20 October 2026.
  7. Elucidating the Design Space of Diffusion-Based Generative Models arxiv.org. Checked 20 October 2026.
  8. Announcing the NeurIPS 2022 Awards – NeurIPS Blog blog.neurips.cc. Checked 20 October 2026.
  9. Guiding a Diffusion Model with a Bad Version of Itself arxiv.org. Checked 20 October 2026.
  10. NeurIPS 2024 Awards neurips.cc. Checked 20 October 2026.
  11. Finite Difference Flow Optimization for RL Post-Training of Text-to-Image Models arxiv.org. Checked 20 October 2026.