Traditional image reconstruction methods often face challenges like noise, artifacts, and blurriness, requiring handcrafted algorithms for effective resolution. In contrast, deep learning techniques, notably Convolutional Neural Networks (CNNs) and Variational Autoencoders (VAEs), present more robust alternat...

Lamps are difficult to market via websites. Renderings and photographs of showrooms rarely fit consumer pref erences and demands and the technical specifications for lighting are unintuitive and difficult to understand for non-experts. This poses a challenge for lighting system manufacturer...

Analyses for biodiversity monitoring based on passive acoustic monitoring (PAM) recordings is time-consuming and chal lenged by the presence of background noise in recordings. Existing models for sound event detection (SED) worked only on certain avian species and the development of fu...

We developed a virtual environment (VE) for nursing students so that they can experience what a person living with schizophrenia constantly hears. In our implementation, Non Player Character (NPC) Eva interacts with the player by recognizing the facial expressions of the players wearing...

This paper introduces a new algorithm for real-time rendering that builds upon bidirectional path tracing, reservoir based spatio-temporal importance resampling, and dynamic diffuse global illumination. The combination of these algorithms produces an image with reduced noise compared to real-time run&...

This paper introduces an enhanced Denosing Autoencoder (DAE) model, incorporating a novel attention mecha nism, for the segmentation of solar coronal loops. This work is based on DAE framework to address the segmenta tion challenges posed by intricate structures of coronal loops which&#...

We investigate the use of data-GIFs, i.e., graphics interchange format files containing short animations, to engage visualization viewers in learning about data visualization design pitfalls. A large number of data visualizations— among which, also several with bad data designs—are generated ever...

Image annotation, also called labeling is a necessary task for any supervised learning approach to obtain ground truth data for model training. This article offers a comprehensive survey of contemporary image annotation tools, grouping freely accessible ones based on their service range,...

Video Anomaly Detection (VAD) plays a crucial role in modern surveillance systems, aiming to identify various anomalies in real-world situations. However, current benchmark datasets predominantly emphasize simple, single frame anomalies such as novel object detection. This narrow focus restricts the&#...

Modern cameras typically offer two types of image states: a minimally processed linear raw RGB image repre senting the raw sensor data, and a highly-processed non-linear image state, such as the sRGB state. The CIE-XYZ color space is a device-independent linear space used as p...

Point cloud registration plays a crucial role in many applications, from robotics and autonomous navigation to medical imaging and 3D scene reconstruction. While the Iterative Closest Point (ICP) algorithm is a well-known shape registration choice, its efficiency and accuracy can be affected...

A traditional computer graphics domain has received an unprecedented boost from the newest developments in generative Artificial Intelligence (GenAI). It affects all areas: from image generation, to face recognition, to object detection, to aerial surveillance, to autonomous car vis...