Progressive Growing of GANs for Improved Quality, Stability, and Variation
- Tero Karras, Timo Aila, S. Laine, J. Lehtinen
- Computer ScienceInternational Conference on Learning…
- 27 October 2017
A new training methodology for generative adversarial networks is described, starting from a low resolution, and adding new layers that model increasingly fine details as training progresses, allowing for images of unprecedented quality.
Analyzing and Improving the Image Quality of StyleGAN
- Tero Karras, S. Laine, M. Aittala, Janne Hellsten, J. Lehtinen, Timo Aila
- Computer ScienceComputer Vision and Pattern Recognition
- 3 December 2019
This work redesigns the generator normalization, revisit progressive growing, and regularize the generator to encourage good conditioning in the mapping from latent codes to images, and thereby redefines the state of the art in unconditional image modeling.
Training Generative Adversarial Networks with Limited Data
- Tero Karras, M. Aittala, Janne Hellsten, S. Laine, J. Lehtinen, Timo Aila
- Computer ScienceNeural Information Processing Systems
- 1 June 2020
It is demonstrated, on several datasets, that good results are now possible using only a few thousand training images, often matching StyleGAN2 results with an order of magnitude fewer images, and is expected to open up new application domains for GANs.
Noise2Noise: Learning Image Restoration without Clean Data
- J. Lehtinen, J. Munkberg, Timo Aila
- Computer ScienceInternational Conference on Machine Learning
- 12 March 2018
It is shown that under certain common circumstances, it is possible to learn to restore signals without ever observing clean ones, at performance close or equal to training using clean exemplars.
GANSpace: Discovering Interpretable GAN Controls
- Erik Härkönen, Aaron Hertzmann, J. Lehtinen, Sylvain Paris
- Computer ScienceNeural Information Processing Systems
- 6 April 2020
This paper describes a simple technique to analyze Generative Adversarial Networks and create interpretable controls for image synthesis, and shows that BigGAN can be controlled with layer-wise inputs in a StyleGAN-like manner.
Alias-Free Generative Adversarial Networks
- Tero Karras, M. Aittala, Timo Aila
- Computer ScienceNeural Information Processing Systems
- 23 June 2021
It is observed that despite their hierarchical convolutional nature, the synthesis process of typical generative adversarial networks depends on absolute pixel coordinates in an unhealthy manner, and small architectural changes are derived that guarantee that unwanted information cannot leak into the hierarchical synthesis process.
Improved Precision and Recall Metric for Assessing Generative Models
- T. Kynkäänniemi, Tero Karras, S. Laine, J. Lehtinen, Timo Aila
- Computer ScienceNeural Information Processing Systems
- 15 April 2019
This work presents an evaluation metric that can separately and reliably measure both the quality and coverage of the samples produced by a generative model and the perceptual quality of individual samples, and extends it to study latent space interpolations.
Few-Shot Unsupervised Image-to-Image Translation
- Ming-Yu Liu, Xun Huang, J. Kautz
- Computer ScienceIEEE International Conference on Computer Vision
- 5 May 2019
This model achieves this few-shot generation capability by coupling an adversarial training scheme with a novel network design, and verifies the effectiveness of the proposed framework through extensive experimental validation and comparisons to several baseline methods on benchmark datasets.
High-Quality Self-Supervised Deep Image Denoising
- S. Laine, Tero Karras, J. Lehtinen, Timo Aila
- Computer ScienceNeural Information Processing Systems
- 29 January 2019
This work builds on a recent technique that removes the need for reference data by employing networks with a "blind spot" in the receptive field, and significantly improves two key aspects: image quality and training efficiency.
Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer
- Wenzheng Chen, Jun Gao, S. Fidler
- Computer ScienceNeural Information Processing Systems
- 3 August 2019
A differentiable rendering framework which allows gradients to be analytically computed for all pixels in an image and to view foreground rasterization as a weighted interpolation of local properties and background rasterized as a distance-based aggregation of global geometry.
...
...