Related papers: Windscreen Optical Quality for AI Algorithms: Refr…
In machine learning, research has traditionally focused on model development, with relatively less attention paid to training data. As model architectures have matured and marginal gains from further refinements diminish, data quality has…
Neural radiance fields (NeRF) are a groundbreaking computer vision technology that enables the generation of high-quality, immersive visual content from multiple viewpoints. This capability has significant advantages for applications such…
To reach the full potential of the new generation of ground based telescopes, an extremely fine adjustment of the phase is required. Wavefront control and correction before detection has therefore become one of the cornerstones of…
Reciprocity is a fundamental principle of wave physics and directly relates to the symmetry in the transmission through a system when interchanging the input and output. The coherent transmission matrix (TM) is a convenient method to…
The rapid progress in deep generative models has led to the creation of incredibly realistic synthetic images that are becoming increasingly difficult to distinguish from real-world data. The widespread use of Variational Models, Diffusion…
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of…
The energy-based methods as the Dispersion Relation (DR) and Response Theory of Optical Forces (RTOF) have been largely applied to obtain the optical forces in the nano-optomechanical devices, in contrast to the Maxwell Stress Tensor (MST).…
The field of automatic image inpainting has progressed rapidly in recent years, but no one has yet proposed a standard method of evaluating algorithms. This absence is due to the problem's challenging nature: image-inpainting algorithms…
3D cameras have emerged as a critical source of information for applications in robotics and autonomous driving. These cameras provide robots with the ability to capture and utilize point clouds, enabling them to navigate their surroundings…
According to the EPA, only 25% of waste is recycled, and just 60% of U.S. municipalities offer curbside recycling. Plastics fare worse, with a recycling rate of only 8%; an additional 16% is incinerated, while the remaining 76% ends up in…
Intrinsic image decomposition and inverse rendering are long-standing problems in computer vision. To evaluate albedo recovery, most algorithms report their quantitative performance with a mean Weighted Human Disagreement Rate (WHDR) metric…
Machine Translation (MT) evaluation metrics assess translation quality automatically. Recently, researchers have employed MT metrics for various new use cases, such as data filtering and translation re-ranking. However, most MT metrics…
In this dissertation, we present a generative model to capture the relation between facial image quality features (like pose, illumination direction, etc) and face recognition performance. Such a model can be used to predict the performance…
The magnetorotational instability (MRI) plays a crucial role in the evolution of many types of accretion disks. It is often studied using ideal-MHD numerical simulations. In principle, such simulations should be numerically converged, i.e.…
High dynamic range (HDR) rendering has the ability to faithfully reproduce the wide luminance ranges in natural scenes, but how to accurately assess the rendering quality is relatively underexplored. Existing quality models are mostly…
Accurately assessing the perceptual quality of face images is crucial, especially with the rapid progress in face restoration and generation. Traditional quality assessment methods often struggle with the unique characteristics of face…
Recent advances in AI enable the automatic generation of visualizations directly from textual prompts using agentic workflows. However, visualizations produced via one-shot generative methods often suffer from insufficient quality,…
We propose a new method for the visual quality assessment of 360-degree (omnidirectional) videos. The proposed method is based on computing multiple spatio-temporal objective quality features on viewports extracted from 360-degree videos. A…
The viability of automated driving is heavily dependent on the performance of perception systems to provide real-time accurate and reliable information for robust decision-making and maneuvers. These systems must perform reliably not only…
This review explores the innovative design to achieve advanced optical functions in natural materials and intricate optical systems inspired by the unique refractive index profiles found in nature. By understanding the physical principles…