Stochastic Super-resolution of Cosmological Simulations with Denoising
Diffusion Models
- URL: http://arxiv.org/abs/2310.06929v1
- Date: Tue, 10 Oct 2023 18:32:11 GMT
- Title: Stochastic Super-resolution of Cosmological Simulations with Denoising
Diffusion Models
- Authors: Andreas Schanz, Florian List, Oliver Hahn
- Abstract summary: We introduce denoising diffusion models as a powerful generative model for super-resolving cosmic large-scale structure predictions.
We demonstrate that our model not only produces convincing super-resolution images and power spectra consistent at the percent level, but is also able to reproduce the diversity of small-scale features consistent with a given low-resolution simulation.
- Score: 3.683202928838613
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In recent years, deep learning models have been successfully employed for
augmenting low-resolution cosmological simulations with small-scale
information, a task known as "super-resolution". So far, these cosmological
super-resolution models have relied on generative adversarial networks (GANs),
which can achieve highly realistic results, but suffer from various
shortcomings (e.g. low sample diversity). We introduce denoising diffusion
models as a powerful generative model for super-resolving cosmic large-scale
structure predictions (as a first proof-of-concept in two dimensions). To
obtain accurate results down to small scales, we develop a new "filter-boosted"
training approach that redistributes the importance of different scales in the
pixel-wise training objective. We demonstrate that our model not only produces
convincing super-resolution images and power spectra consistent at the percent
level, but is also able to reproduce the diversity of small-scale features
consistent with a given low-resolution simulation. This enables uncertainty
quantification for the generated small-scale features, which is critical for
the usefulness of such super-resolution models as a viable surrogate model for
cosmic structure formation.
Related papers
- DEEM: Diffusion Models Serve as the Eyes of Large Language Models for Image Perception [66.88792390480343]
We propose DEEM, a simple and effective approach that utilizes the generative feedback of diffusion models to align the semantic distributions of the image encoder.
DEEM exhibits enhanced robustness and a superior capacity to alleviate hallucinations while utilizing fewer trainable parameters, less pre-training data, and a smaller base model size.
arXiv Detail & Related papers (2024-05-24T05:46:04Z) - Domain Transfer in Latent Space (DTLS) Wins on Image Super-Resolution --
a Non-Denoising Model [13.326634982790528]
We propose a simple approach which gets away from using Gaussian noise but adopts some basic structures of diffusion models for efficient image super-resolution.
Experimental results show that our method outperforms not only state-of-the-art large scale super resolution models, but also the current diffusion models for image super-resolution.
arXiv Detail & Related papers (2023-11-04T09:57:50Z) - PSRFlow: Probabilistic Super Resolution with Flow-Based Models for
Scientific Data [11.15523311079383]
PSRFlow is a novel normalizing flow-based generative model for scientific data super-resolution.
Our results demonstrate superior performance and robust uncertainty quantification compared with existing methods.
arXiv Detail & Related papers (2023-08-08T22:10:29Z) - ACDMSR: Accelerated Conditional Diffusion Models for Single Image
Super-Resolution [84.73658185158222]
We propose a diffusion model-based super-resolution method called ACDMSR.
Our method adapts the standard diffusion model to perform super-resolution through a deterministic iterative denoising process.
Our approach generates more visually realistic counterparts for low-resolution images, emphasizing its effectiveness in practical scenarios.
arXiv Detail & Related papers (2023-07-03T06:49:04Z) - Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance.
We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring.
Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
arXiv Detail & Related papers (2023-05-22T12:18:20Z) - Implicit Diffusion Models for Continuous Super-Resolution [65.45848137914592]
This paper introduces an Implicit Diffusion Model (IDM) for high-fidelity continuous image super-resolution.
IDM integrates an implicit neural representation and a denoising diffusion model in a unified end-to-end framework.
The scaling factor regulates the resolution and accordingly modulates the proportion of the LR information and generated features in the final output.
arXiv Detail & Related papers (2023-03-29T07:02:20Z) - Learning multi-scale local conditional probability models of images [7.07848787073901]
Deep neural networks can learn powerful prior probability models for images, as evidenced by the high-quality generations obtained with recent score-based diffusion methods.
But the means by which these networks capture complex global statistical structure, apparently without suffering from the curse of dimensionality, remain a mystery.
We incorporate diffusion methods into a multi-scale decomposition, reducing dimensionality by assuming a stationary local Markov model for wavelet coefficients conditioned on coarser-scale coefficients.
arXiv Detail & Related papers (2023-03-06T09:23:14Z) - Uncovering the Over-smoothing Challenge in Image Super-Resolution: Entropy-based Quantification and Contrastive Optimization [67.99082021804145]
We propose an explicit solution to the COO problem, called Detail Enhanced Contrastive Loss (DECLoss)
DECLoss utilizes the clustering property of contrastive learning to directly reduce the variance of the potential high-resolution distribution.
We evaluate DECLoss on multiple super-resolution benchmarks and demonstrate that it improves the perceptual quality of PSNR-oriented models.
arXiv Detail & Related papers (2022-01-04T08:30:09Z) - A Latent Encoder Coupled Generative Adversarial Network (LE-GAN) for
Efficient Hyperspectral Image Super-resolution [3.1023808510465627]
generative adversarial network (GAN) has proven to be an effective deep learning framework for image super-resolution.
To alleviate the problem of mode collapse, this work has proposed a novel GAN model coupled with a latent encoder (LE-GAN)
LE-GAN can map the generated spectral-spatial features from the image space to the latent space and produce a coupling component to regularise the generated samples.
arXiv Detail & Related papers (2021-11-16T18:40:19Z) - Super-resolving Dark Matter Halos using Generative Deep Learning [77.79867381335231]
Generative deep learning methods built upon Convolutional Neural Networks (CNNs) provide a great tool for predicting non-linear structure in cosmology.
In this work we predict high resolution dark matter halos from large scale, low resolution dark matter only simulations.
arXiv Detail & Related papers (2021-11-11T18:59:07Z) - Learning Integrodifferential Models for Image Denoising [14.404339094377319]
We introduce an integrodifferential extension of the edge-enhancing anisotropic diffusion model for image denoising.
By accumulating weighted structural information on multiple scales, our model is the first to create anisotropy through multiscale integration.
arXiv Detail & Related papers (2020-10-21T10:50:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.