1 code implementation • 4 Jun 2024 • Tero Karras, Miika Aittala, Tuomas Kynkäänniemi, Jaakko Lehtinen, Timo Aila, Samuli Laine
The primary axes of interest in image-generating diffusion models are image quality, the amount of variation in the results, and how well the results align with a given condition, e. g., a class label or a text prompt.
Ranked #1 on
Image Generation
on ImageNet 512x512
1 code implementation • 11 Apr 2024 • Tuomas Kynkäänniemi, Miika Aittala, Tero Karras, Samuli Laine, Timo Aila, Jaakko Lehtinen
We show that guidance is clearly harmful toward the beginning of the chain (high noise levels), largely unnecessary toward the end (low noise levels), and only beneficial in the middle.
Ranked #6 on
Image Generation
on ImageNet 512x512
6 code implementations • CVPR 2024 • Tero Karras, Miika Aittala, Jaakko Lehtinen, Janne Hellsten, Timo Aila, Samuli Laine
Diffusion models currently dominate the field of data-driven image synthesis with their unparalleled scaling to large datasets.
Ranked #17 on
Image Generation
on ImageNet 512x512
1 code implementation • ICCV 2023 • Eric R. Chan, Koki Nagano, Matthew A. Chan, Alexander W. Bergman, Jeong Joon Park, Axel Levy, Miika Aittala, Shalini De Mello, Tero Karras, Gordon Wetzstein
We present a diffusion-based model for 3D-aware generative novel view synthesis from as few as a single input image.
no code implementations • 14 Dec 2022 • Onni Kosomaa, Samuli Laine, Tero Karras, Miika Aittala, Jaakko Lehtinen
We propose a deep learning method for 3D volumetric reconstruction in low-dose helical cone-beam computed tomography.
2 code implementations • 2 Nov 2022 • Yogesh Balaji, Seungjun Nah, Xun Huang, Arash Vahdat, Jiaming Song, Qinsheng Zhang, Karsten Kreis, Miika Aittala, Timo Aila, Samuli Laine, Bryan Catanzaro, Tero Karras, Ming-Yu Liu
Therefore, in contrast to existing works, we propose to train an ensemble of text-to-image diffusion models specialized for different synthesis stages.
Ranked #14 on
Text-to-Image Generation
on MS COCO
1 code implementation • 4 Jul 2022 • Erik Härkönen, Miika Aittala, Tuomas Kynkäänniemi, Samuli Laine, Timo Aila, Jaakko Lehtinen
We introduce the problem of disentangling time-lapse sequences in a way that allows separate, after-the-fact control of overall trends, cyclic effects, and random effects in the images, and describe a technique based on data-driven generative models that achieves this goal.
1 code implementation • 7 Jun 2022 • Tim Brooks, Janne Hellsten, Miika Aittala, Ting-Chun Wang, Timo Aila, Jaakko Lehtinen, Ming-Yu Liu, Alexei A. Efros, Tero Karras
Existing video generation methods often fail to produce new content as a function of time while maintaining consistencies expected in real environments, such as plausible dynamics and object persistence.
18 code implementations • 1 Jun 2022 • Tero Karras, Miika Aittala, Timo Aila, Samuli Laine
We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices.
2 code implementations • 11 Mar 2022 • Tuomas Kynkäänniemi, Tero Karras, Miika Aittala, Timo Aila, Jaakko Lehtinen
Fr\'echet Inception Distance (FID) is the primary metric for ranking models in data-driven generative modeling.
no code implementations • ICCV 2021 • Prafull Sharma, Miika Aittala, Yoav Y. Schechner, Antonio Torralba, Gregory W. Wornell, William T. Freeman, Fredo Durand
We present a passive non-line-of-sight method that infers the number of people or activity of a person from the observation of a blank wall in an unknown room.
7 code implementations • NeurIPS 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.
Ranked #1 on
Image Generation
on FFHQ-U
28 code implementations • NeurIPS 2020 • Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, Timo Aila
We also find that the widely used CIFAR-10 is, in fact, a limited data benchmark, and improve the record FID from 5. 59 to 2. 42.
Ranked #1 on
Conditional Image Generation
on ArtBench-10 (32x32)
1 code implementation • NeurIPS 2019 • Miika Aittala, Prafull Sharma, Lukas Murmann, Adam B. Yedidia, Gregory W. Wornell, William T. Freeman, Fredo Durand
We recover a video of the motion taking place in a hidden scene by observing changes in indirect illumination in a nearby uncalibrated visible region.
126 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.
Ranked #1 on
Image Generation
on LSUN Car 256 x 256
no code implementations • ICCV 2019 • Lukas Murmann, Michael Gharbi, Miika Aittala, Fredo Durand
Collections of images under a single, uncontrolled illumination have enabled the rapid advancement of core computer vision tasks like classification, detection, and segmentation.
1 code implementation • 27 Jun 2019 • Valentin Deschaintre, Miika Aittala, Fredo Durand, George Drettakis, Adrien Bousseau
Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph.
Graphics I.3
1 code implementation • 18 Apr 2019 • Ronnachai Jaroensri, Camille Biscarrat, Miika Aittala, Frédo Durand
Unfortunately, the commonly used additive white noise (AWGN) models do not accurately reproduce the noise and the degradation encountered on these inputs.
1 code implementation • 23 Oct 2018 • Valentin Deschaintre, Miika Aittala, Fredo Durand, George Drettakis, Adrien Bousseau
Texture, highlights, and shading are some of many visual cues that allow humans to perceive material appearance in single pictures.
Graphics I.3
no code implementations • ECCV 2018 • Miika Aittala, Fredo Durand
We propose a neural approach for fusing an arbitrary-length burst of photographs suffering from severe camera shake and noise into a sharp and noise-free image.
1 code implementation • SIGGRAPH 2018 • Tzu-Mao Li, Miika Aittala, Frédo Durand, Jaakko Lehtinen
We introduce a general-purpose differentiable ray tracer, which, to our knowledge, is the first comprehensive solution that is able to compute derivatives of scalar functions over a rendered image with respect to arbitrary scene parameters such as camera pose, scene geometry, materials, and lighting parameters.
21 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.