Related papers: DrizzlePac 2.0 - Introducing New Features
HEALPix -- the Hierarchical Equal Area isoLatitude Pixelization -- has become a standard in high-energy and gravitational wave astronomy. Originally developed to improve the efficiency of all-sky Fourier analyses, it is now also utilized to…
Several supervised networks exist that remove haze information from underwater images using paired datasets and pixel-wise loss functions. However, training these networks requires large amounts of paired data which is cumbersome, complex…
Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on collecting human or AI preferences, which can be costly and…
I developed a new pure-python pipeline to reduce photometric and polarimetric data: ASTROPOP. It has been designed and optimized to work fully automated with the IAGPOL polarimeter of Pico dos Dias observatory (OPD, Brazil) and can reduce…
In this paper, we present feature-based technique for construction of mosaic image from underwater video sequence, which suffers from parallax distortion due to propagation properties of light in the underwater environment. The most of the…
Large, high-resolution space-based imaging surveys produce a volume of data that is difficult to present to the public in a comprehensible way. While megapixel-sized images can still be printed out or downloaded via the World Wide Web, this…
The quality of images captured in outdoor environments can be affected by poor weather conditions such as fog, dust, and atmospheric scattering of other particles. This problem can bring extra challenges to high-level computer vision tasks…
In an era where astronomical data is expanding at an unprecedented rate, the importance of data sharing and accessibility among astronomy archives cannot be overstated. Since the 1990s, an international partnership between the Space…
Raindrops adhering to the lens of UAVs can obstruct visibility of the background scene and degrade image quality. Despite recent progress in image deraining methods and datasets, there is a lack of focus on raindrop removal from UAV aerial…
In the last decade a new generation of telescopes and sensors has allowed the production of a very large amount of data and astronomy has become a data-rich science. New automatic methods largely based on machine learning are needed to cope…
The Timepix particle tracking telescope has been developed as part of the LHCb VELO Upgrade project, supported by the Medipix Collaboration and the AIDA framework. It is a primary piece of infrastructure for the VELO Upgrade project and is…
This paper introduces a modular, non-deep learning method for filtering and refining sparse correspondences in image matching. Assuming that motion flow within the scene can be approximated by local homography transformations, matches are…
The images provided by the Advanced Camera for Surveys at the Hubble Space Telescope (ACS/HST) have the amazing spacial resolution of 0".05/pixel. Therefore, it is possible to resolve individual stars in nearby galaxies and, in particular,…
We present an algorithm capable of detecting diffuse, dim sources of any size in an astronomical image. These sources often defeat traditional methods for source finding, which expand regions around points of high intensity. Extended…
Image editing has made great progress on planar images, but panoramic image editing remains underexplored. Due to their spherical geometry and projection distortions, panoramic images present three key challenges: boundary discontinuity,…
Adverse weather conditions often impair the quality of captured images, inevitably inducing cutting-edge object detection models for advanced driver assistance systems (ADAS) and autonomous driving. In this paper, we raise an intriguing…
Recent studies have demonstrated significant progress in aligning text-to-image diffusion models with human preference via Reinforcement Learning from Human Feedback. However, while existing methods achieve high scores on automated reward…
Image dehazing, addressing atmospheric interference like fog and haze, remains a pervasive challenge crucial for robust vision applications such as surveillance and remote sensing under adverse visibility. While various methodologies have…
Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels. Many recent mixup methods focus on cutting and pasting two or more…
Reducing the atmospheric haze and enhancing image clarity is crucial for computer vision applications. The lack of real-life hazy ground truth images necessitates synthetic datasets, which often lack diverse haze types, impeding effective…