Samuli Laine
Computer Vision and Pattern Recognition · 2009–2023
A researcher in the Science corpus: 22 papers; trusts 2,057 researchers and is trusted by 12,649 researchers here, as inferred from the citation graph.
Subfields
- Computer Vision and Pattern Recognition — 605 citations into it; #197 of 21,973 by trust here, #183 by citations
- Generative Models — 340 citations into it; #17 of 1,963 by trust here, #24 by citations
- Artificial Intelligence — 329 citations into it; #1,376 of 36,961 by trust here, #4,126 by citations
- Optimization & Training — 104 citations into it
- Computer Graphics and Computer-Aided Design — 72 citations into it; #794 of 1,641 by trust here, #633 by citations
- Statistical and Nonlinear Physics — 65 citations into it; #2,977 of 10,175 by trust here, #790 by citations
- Model Architectures — 60 citations into it; #808 of 2,288 by trust here, #822 by citations
- Representation & Self-Supervised Learning — 57 citations into it; #154 of 3,156 by trust here, #524 by citations
Whom Samuli Laine trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Alex Krizhevsky
- Kaiming He
- Yoshua Bengio
- Karen Simonyan
- Yann LeCun
- Ilya Sutskever
- Christian Szegedy
- Tim Salimans
Who trusts Samuli Laine overall
- Richard Zhang
- Tero Karras
- Jun-Yan Zhu
- Axel Sauer
- Yang Song
- Yujun Shen
- Yuval Alaluf
- Weihao Xia
- Andrea Vedaldi
- Bolei Zhou
Papers from Samuli Laine's perspective
Ordered by how strongly the researchers Samuli Laine trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Gradient-based learning applied to document recognition
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- ImageNet Large Scale Visual Recognition Challenge
- Learning Multiple Layers of Features from Tiny Images
Their papers
- Progressive Growing of GANs for Improved Quality, Stability, and Variation (2017) — 8,667 citations
- A Style-Based Generator Architecture for Generative Adversarial Networks (2018) — 13,265 citations
- Analyzing and Improving the Image Quality of StyleGAN (2019) — 7,107 citations
- Temporal Ensembling for Semi-Supervised Learning (2016) — 2,908 citations
- Training Generative Adversarial Networks with Limited Data (2020) — 2,283 citations
- Elucidating the Design Space of Diffusion-Based Generative Models (2022) — 3,661 citations
- Improved Precision and Recall Metric for Assessing Generative Models (2019) — 1,312 citations
- eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers (2022) — 1,087 citations
- Alias-Free Generative Adversarial Networks (2021) — 2,077 citations
- Noise2Noise: Learning Image Restoration without Clean Data (2018) — 2,082 citations
- Audio-driven facial animation by joint end-to-end learning of pose and emotion (2017) — 486 citations
- Production-level facial performance capture using deep convolutional neural networks (2016) — 104 citations
- Efficient Sparse Voxel Octrees (2010) — 343 citations
- Modular primitives for high-performance differentiable rendering (2020) — 656 citations
- StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis (2023) — 300 citations
- Semi-supervised semantic segmentation needs strong, varied perturbations (2019) — 378 citations
- Semi-supervised semantic segmentation needs strong, high-dimensional perturbations (2019) — 137 citations
- Feature-Based Metrics for Exploring the Latent Space of Generative Models (2018) — 47 citations
- Analyzing and Improving the Training Dynamics of Diffusion Models (2023) — 442 citations
- A Style-Based Generator Architecture for Generative Adversarial Networks (2020) — 219 citations