Related papers: VIP: Vortex Image Processing package for high-cont…
The ubiquitous and demonstrably suboptimal choice of resizing images to a fixed resolution before processing them with computer vision models has not yet been successfully challenged. However, models such as the Vision Transformer (ViT)…
Multiplexed imaging data are revolutionizing our understanding of the composition and organization of tissues and tumors. A critical aspect of such tissue profiling is quantifying the spatial relationship relationships among cells at…
Efficiency and robustness are the essential criteria for the visual-inertial odometry (VIO) system. To process massive visual data, the high cost on CPU resources and computation latency limits VIO's possibility in integration with other…
Hi-5 is a high-contrast (or high dynamic range) infrared imager project for the VLTI. Its main goal is to characterize young extra-solar planetary systems and exozodiacal dust around southern main-sequence stars. In this paper, we present…
Vision Transformers (ViTs) have emerged as the backbone of many segmentation models, consistently achieving state-of-the-art (SOTA) performance. However, their success comes at a significant computational cost. Image token pruning is one of…
Vision Transformer (ViT) is becoming widely popular in automating accurate disease diagnosis in medical imaging owing to its robust self-attention mechanism. However, ViTs remain vulnerable to adversarial attacks that may thwart the…
High-resolution volumetric imaging techniques, such as X-ray tomography and advanced microscopy, generate increasingly large datasets that challenge existing tools for efficient processing, segmentation, and interactive exploration. This…
Context. The direct detection of exoplanets with high-contrast imaging requires advanced data processing methods to disentangle potential planetary signals from bright quasi-static speckles. Among them, angular differential imaging (ADI)…
The possibility of carrying out a meaningful forensics analysis on printed and scanned images plays a major role in many applications. First of all, printed documents are often associated with criminal activities, such as terrorist plans,…
Although using convolutional neural networks (CNNs) as backbones achieves great successes in computer vision, this work investigates a simple backbone network useful for many dense prediction tasks without convolutions. Unlike the…
Vision-Language Pre-training (VLP) methods based on object detection enjoy the rich knowledge of fine-grained object-text alignment but at the cost of computationally expensive inference. Recent Visual-Transformer (ViT)-based approaches…
We present the pyKLIP-CHARIS post-processing pipeline, a Python library that reduces high contrast imaging data for the CHARIS integral field spectrograph used with the SCExAO project on the Subaru Telescope. The pipeline is a part of the…
Vision transformers have shown great potential in various computer vision tasks owing to their strong capability to model long-range dependency using the self-attention mechanism. Nevertheless, they treat an image as a 1D sequence of visual…
Understanding porous media flow is inherently a multi-scale challenge, where at the core lies the aggregation of pore-level processes to a continuum, or Darcy-scale, description. This challenge is directly mirrored in image processing,…
The Herschel Interactive Processing Environment (HIPE) was developed by the European Space Agency (ESA) in collaboration with NASA and the Herschel Instrument Control Centres to provide the astronomical community a complete environment to…
Improving the throughput of molecular docking, a computationally intensive phase of the virtual screening process, is a highly sought area of research since it has a significant weight in the drug designing process. With such improvements,…
DADApy is a python software package for analysing and characterising high-dimensional data manifolds. It provides methods for estimating the intrinsic dimension and the probability density, for performing density-based clustering and for…
Many technologies have been developed to help improve spatial resolution of observational images for ground-based solar telescopes, such as adaptive optics (AO) systems and post-processing reconstruction. As any AO system correction is only…
We present VIPGI, an automatized human supervised reduction environment, developed within the VIRMOS project to handle VIMOS guaranteed time data. VIPGI is now offered to the international community to be used on site in Milano and…
The aim of this work is to explore the potential of pre-trained vision-language models (VLMs) for universal detection of AI-generated images. We develop a lightweight detection strategy based on CLIP features and study its performance in a…