Search Results for author: Miika Aittala

Found 18 papers, 12 papers with code

Projection-Domain Self-Supervision for Volumetric Helical CT Reconstruction

no code implementations14 Dec 2022 Onni Kosomaa, Samuli Laine, Tero Karras, Miika Aittala, Jaakko Lehtinen

We propose a deep learning method for three-dimensional reconstruction in low-dose helical cone-beam computed tomography.

Disentangling Random and Cyclic Effects in Time-Lapse Sequences

1 code implementation4 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.

Generating Long Videos of Dynamic Scenes

no code implementations7 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.

Video Generation

Elucidating the Design Space of Diffusion-Based Generative Models

5 code implementations1 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.

Image Generation

The Role of ImageNet Classes in Fréchet Inception Distance

1 code implementation11 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.

What You Can Learn by Staring at a Blank Wall

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.

Alias-Free Generative Adversarial Networks

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.

Image Generation

Computational Mirrors: Blind Inverse Light Transport by Deep Matrix Factorization

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.

Analyzing and Improving the Image Quality of StyleGAN

118 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.

Conditional Image Generation

A Dataset of Multi-Illumination Images in the Wild

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.

Image Relighting

Flexible SVBRDF Capture with a Multi-Image Deep Network

1 code implementation27 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

Generating Training Data for Denoising Real RGB Images via Camera Pipeline Simulation

1 code implementation18 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.

Demosaicking Denoising +1

Single-Image SVBRDF Capture with a Rendering-Aware Deep Network

1 code implementation23 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

Burst Image Deblurring Using Permutation Invariant Convolutional Neural Networks

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.

Deblurring Image Deblurring +1

Differentiable Monte Carlo Ray Tracing through Edge Sampling

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.

Noise2Noise: Learning Image Restoration without Clean Data

20 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.

BIG-bench Machine Learning Image Restoration +1

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