相关论文: Astrophotography turbulence mitigation via generat…

Traditionally, the main focus of image super-resolution techniques is on recovering the most likely high-quality images from low-quality images, using a one-to-one low- to high-resolution mapping. Proceeding that way, we ignore the fact…

How do diffusion generative models convert pure noise into meaningful images? In a variety of pretrained diffusion models (including conditional latent space models like Stable Diffusion), we observe that the reverse diffusion process that…

Atmospheric turbulence (AT) introduces severe degradations, such as rippling, blur, and intensity fluctuations, that hinder both image quality and downstream vision tasks like target detection. While recent deep learning-based approaches…

The inverse problem of backward diffusion is known to be ill-posed and highly unstable. Backward diffusion processes appear naturally in image enhancement and deblurring applications. It is therefore greatly desirable to establish a…

Phase referencing is a standard calibration procedure in radio interferometry. It allows to detect weak sources by using quasi-simultaneous observations of closeby sources acting as calibrators. Therefore, it is assumed that, for each…

Old-photo face restoration poses significant challenges due to compounded degradations such as breakage, fading, and severe blur. Existing pre-trained diffusion-guided methods either rely on explicit degradation priors or global statistical…

Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained…

Unbiased sky background modeling is crucial for the analysis of deep wide-field images, but it remains a major challenge in low surface brightness astronomy. Traditional image processing algorithms are often designed to produce artificially…

Recent advancements in 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF) have achieved impressive results in real-time 3D reconstruction and novel view synthesis. However, these methods struggle in large-scale, unconstrained…

The generation and evolution of astrophysical magnetic fields occurs largely through the action of turbulence. In many situations, the magnetic field is strong enough to influence many important properties of turbulence itself. Numerical…

Deep MRI reconstruction is commonly performed with conditional models that de-alias undersampled acquisitions to recover images consistent with fully-sampled data. Since conditional models are trained with knowledge of the imaging operator,…

Forecasting optical turbulence in the Earth's atmosphere has been an ambitious challenge for the astronomical scientific community for several decades. While earlier research primarily focused on whether it was possible to predict optical…

Camera anomalies like rain or dust can severelydegrade image quality and its related tasks, such as localizationand segmentation. In this work we address this importantissue by implementing a pre-processing step that can effectivelymitigate…

Diffusion models (DMs) have exhibited remarkable efficacy in various image restoration tasks. However, existing approaches typically operate within the high-dimensional pixel space, resulting in high computational overhead. While methods…

Do contemporary diffusion models preserve the class geometry of hyperspherical data? Standard diffusion models rely on isotropic Gaussian noise in the forward process, inherently favoring Euclidean spaces. However, many real-world problems…

Image denoising based on deep learning has witnessed significant advancements in recent years. However, existing deep learning methods lack quantitative control of the deviation or error on denoised images. The neural networks Self2Self is…

Generating ground-level views and coherent 3D site models from aerial-only imagery is challenging due to extreme viewpoint changes, missing intermediate observations, and large scale variations. Existing methods either refine renderings…

We consider the problem of trustworthy image restoration, taking the form of a constrained optimization over the prior density. To this end, we develop generative models for the task of image super-resolution that respect the degradation…

Photographs taken in adverse weather conditions often suffer from blurriness, occlusion, and low brightness due to interference from rain, snow, and fog. These issues can significantly hinder the performance of subsequent computer vision…

We present a self-supervised and self-calibrating multi-shot approach to imaging through atmospheric turbulence, called TurbuGAN. Our approach requires no paired training data, adapts itself to the distribution of the turbulence, leverages…