Related papers: Autoencoding Labeled Interpolator, Inferring Param…
The polarized images of the supermassive black hole Messier 87* (M87*) produced by the Event Horizon Telescope (EHT) provide a direct view of the near-horizon emission from a black hole accretion and jet system. The EHT theoretical analysis…
Semantic image inpainting is a challenging task where large missing regions have to be filled based on the available visual data. Existing methods which extract information from only a single image generally produce unsatisfactory results…
Recent advancements in event-based recognition have demonstrated significant promise, yet most existing approaches rely on extensive training, limiting their adaptability for efficient processing of event-driven visual content. Meanwhile,…
Accreting massive black holes (MBHs, with M$_\bullet > 10^3$ M$_{\odot}$) are known for their panchromatic emission, spanning from radio to gamma rays. While MBHs accreting at significant fractions of their Eddington rate are readily…
Black holes are among the most compelling predictions of general relativity (GR) and are now strongly supported by observations from gravitational-wave detectors and the Event Horizon Telescope (EHT). While standard black hole solutions…
Synthetic data generation represents a significant advancement in boosting the performance of machine learning (ML) models, particularly in fields where data acquisition is challenging, such as echocardiography. The acquisition and labeling…
In view of the upcoming observations with the Event Horizon Telescope (EHT), we present our thoughts on the immediate environment of an astrophysical black hole. We are concerned that two approximations used in general relativistic…
Open-ended image generation is no longer a simple prompt-to-image problem. High-quality generation often requires an agent to combine a model's internal generative ability with external resources. As requests become more diverse and…
In this paper, we treat the image generation task using an autoencoder, a representative latent model. Unlike many studies regularizing the latent variable's distribution by assuming a manually specified prior, we approach the image…
Automated medical report generation has become increasingly important in medical analysis. It can produce computer-aided diagnosis descriptions and thus significantly alleviate the doctors' work. Inspired by the huge success of neural…
The Event Horizon Telescope (EHT) collaboration has produced the first resolved images of the supermassive black holes at the centre of our galaxy and at the centre of the elliptical galaxy M87. As both technology and analysis pipelines…
The Event Horizon Telescope (EHT) delivered the first image of a black hole by capturing the light from its surrounding accretion flow, revealing structure but not dynamics. Simulations of black hole accretion dynamics are essential for…
Auto-encoders are perhaps the best-known non-probabilistic methods for representation learning. They are conceptually simple and easy to train. Recent theoretical work has shed light on their ability to capture manifold structure, and drawn…
The reconstruction of the polarization of a source in radio interferometry is a challenging calibration problem since the reconstruction strongly depends on the gains and leakages that need to be inferred along with the image. This is…
Image synthesis is a core problem in modern deep learning, and many recent architectures such as autoencoders and Generative Adversarial networks produce spectacular results on highly complex data, such as images of faces or landscapes.…
Existing image inpainting methods often produce artifacts when dealing with large holes in real applications. To address this challenge, we propose an iterative inpainting method with a feedback mechanism. Specifically, we introduce a deep…
Most of the artificial lights fluctuate in response to the grid's alternating current and exhibit subtle variations in terms of both intensity and spectrum, providing the potential to estimate the Electric Network Frequency (ENF) from…
Recording fast motion in a high FPS (frame-per-second) requires expensive high-speed cameras. As an alternative, interpolating low-FPS videos from commodity cameras has attracted significant attention. If only low-FPS videos are available,…
The Event Horizon Telescope has produced resolved images of the supermassive black holes Sgr A* and M87*, which present the largest shadows on the sky. In the next decade, technological improvements and extensions to the array will enable…
Projector photometric compensation aims to modify a projector input image such that it can compensate for disturbance from the appearance of projection surface. In this paper, for the first time, we formulate the compensation problem as an…