Search Results for author: Samuli Laine

Found 12 papers, 12 papers with code

Alias-Free Generative Adversarial Networks

6 code implementations23 Jun 2021 Tero Karras, Miika Aittala, Samuli Laine, Erik Härkönen, Janne Hellsten, Jaakko Lehtinen, Timo Aila

We observe that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner.

Image Generation

Modular Primitives for High-Performance Differentiable Rendering

1 code implementation6 Nov 2020 Samuli Laine, Janne Hellsten, Tero Karras, Yeongho Seol, Jaakko Lehtinen, Timo Aila

We present a modular differentiable renderer design that yields performance superior to previous methods by leveraging existing, highly optimized hardware graphics pipelines.

Analyzing and Improving the Image Quality of StyleGAN

104 code implementations CVPR 2020 Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, Timo Aila

Overall, our improved model redefines the state of the art in unconditional image modeling, both in terms of existing distribution quality metrics as well as perceived image quality.

Image Generation

Semi-supervised semantic segmentation needs strong, varied perturbations

3 code implementations5 Jun 2019 Geoff French, Samuli Laine, Timo Aila, Michal Mackiewicz, Graham Finlayson

We analyze the problem of semantic segmentation and find that its' distribution does not exhibit low density regions separating classes and offer this as an explanation for why semi-supervised segmentation is a challenging problem, with only a few reports of success.

General Classification Semi-Supervised Semantic Segmentation

Improved Precision and Recall Metric for Assessing Generative Models

4 code implementations NeurIPS 2019 Tuomas Kynkäänniemi, Tero Karras, Samuli Laine, Jaakko Lehtinen, Timo Aila

The ability to automatically estimate the quality and coverage of the samples produced by a generative model is a vital requirement for driving algorithm research.

Image Generation

High-Quality Self-Supervised Deep Image Denoising

2 code implementations NeurIPS 2019 Samuli Laine, Tero Karras, Jaakko Lehtinen, Timo Aila

We describe a novel method for training high-quality image denoising models based on unorganized collections of corrupted images.

Image Denoising

A Style-Based Generator Architecture for Generative Adversarial Networks

74 code implementations CVPR 2019 Tero Karras, Samuli Laine, Timo Aila

We propose an alternative generator architecture for generative adversarial networks, borrowing from style transfer literature.

Image Generation

Noise2Noise: Learning Image Restoration without Clean Data

18 code implementations ICML 2018 Jaakko Lehtinen, Jacob Munkberg, Jon Hasselgren, Samuli Laine, Tero Karras, Miika Aittala, Timo Aila

We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using clean data, without explicit image priors or likelihood models of the corruption.

Image Restoration Salt-And-Pepper Noise Removal

Temporal Ensembling for Semi-Supervised Learning

6 code implementations7 Oct 2016 Samuli Laine, Timo Aila

In this paper, we present a simple and efficient method for training deep neural networks in a semi-supervised setting where only a small portion of training data is labeled.

General Classification Semi-Supervised Image Classification

Production-Level Facial Performance Capture Using Deep Convolutional Neural Networks

1 code implementation21 Sep 2016 Samuli Laine, Tero Karras, Timo Aila, Antti Herva, Shunsuke Saito, Ronald Yu, Hao Li, Jaakko Lehtinen

We present a real-time deep learning framework for video-based facial performance capture -- the dense 3D tracking of an actor's face given a monocular video.

Cannot find the paper you are looking for? You can Submit a new open access paper.