相关论文: A Comparative Study on Generative Models for High …

Automatic colorization of images without human intervention has been a subject of interest in the machine learning community for a brief period of time. Assigning color to an image is a highly ill-posed problem because of its innate nature…

Facial recognition using deep convolutional neural networks relies on the availability of large datasets of face images. Many examples of identities are needed, and for each identity, a large variety of images are needed in order for the…

The solar granulation is known for a long time to be a surface manifestation of convection. Thanks to the current space-borne missions CoRoT and Kepler, it is now possible to observe in disk-integrated intensity the signature of this…

Generative models make huge progress to the photorealistic image synthesis in recent years. To enable human to steer the image generation process and customize the output, many works explore the interpretable dimensions of the latent space…

Image segmentation is important in medical imaging, providing valuable, quantitative information for clinical decision-making in diagnosis, therapy, and intervention. The state-of-the-art in automated segmentation remains supervised…

Recent work has shown significant progress in the direction of synthetic data generation using Generative Adversarial Networks (GANs). GANs have been applied in many fields of computer vision including text-to-image conversion, domain…

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…

Observed records of climate extremes provide an incomplete view of risk, missing "unseen" events beyond historical experience. Ignoring spatial dependence further underestimates hazards striking multiple locations simultaneously. We…

In this paper, we perform an in-depth study of the properties and applications of aligned generative models. We refer to two models as aligned if they share the same architecture, and one of them (the child) is obtained from the other (the…

Many computer vision tasks rely on labeled data. Rapid progress in generative modeling has led to the ability to synthesize photorealistic images. However, controlling specific aspects of the generation process such that the data can be…

Imaging under extremely low-light conditions presents a significant challenge and is an ill-posed problem due to the low signal-to-noise ratio (SNR) caused by minimal photon capture. Previously, diffusion models have been used for multiple…

Sunspot numbers provide the longest continuous record of solar activity and remain a key index for heliophysical research and space-weather applications. Standard sunspot determination relies on visual inspection and algorithmic…

Generative image modeling techniques such as GAN demonstrate highly convincing image generation result. However, user interaction is often necessary to obtain the desired results. Existing attempts add interactivity but require either…

The generative priors of pre-trained latent diffusion models (DMs) have demonstrated great potential to enhance the visual quality of image super-resolution (SR) results. However, the noise sampling process in DMs introduces randomness in…

Stellar XUV (X-ray and extreme ultraviolet) emission drives the heating and chemical reactions in planetary atmospheres and protoplanetary disks, and therefore, a proper estimation of a stellar XUV spectrum is required for their studies.…

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…

Generative models, such as GANs, learn an explicit low-dimensional representation of a particular class of images, and so they may be used as natural image priors for solving inverse problems such as image restoration and compressive…

In this research work we have proposed high-level ChildDiffusion framework capable of generating photorealistic child facial samples and further embedding several intelligent augmentations on child facial data using short text prompts,…

This paper presents a novel application of Generative Adverserial Networks (GANs) to study visual aspects of social processes. I train a a StyleGAN2-model on a custom dataset of 14,564 images of London, sourced from Google Streetview taken…

Long-term high-cadence measurements of stellar spectral variability are fundamental to better understand stellar atmospheric properties and stellar magnetism. These, in turn, are fundamental for the detectability of exoplanets as well as…