Related papers: PIV/BOS Synthetic Image Generation in Variable Den…
Although Monte Carlo path tracing is a simple and effective algorithm to synthesize photo-realistic images, it is often very slow to converge to noise-free results when involving complex global illumination. One of the most successful…
Text-to-image models give rise to workflows which often begin with an exploration step, where users sift through a large collection of generated images. The global nature of the text-to-image generation process prevents users from narrowing…
In the past, computer vision systems for digitized documents could rely on systematically captured, high-quality scans. Today, transactions involving digital documents are more likely to start as mobile phone photo uploads taken by…
Motion synthesis in real-world 3D scenes has recently attracted much attention. However, the static environment assumption made by most current methods usually cannot be satisfied especially for real-time motion synthesis in scanned point…
Evaluation of AI systems often requires synthetic test cases, particularly for rare or safety-critical conditions that are difficult to observe in operational data. Generative AI offers a promising approach for producing such data through…
We describe a technique of image analysis providing the time resolved shape of a water surface simultaneously with the three-component velocity field on this surface. The method relies on a combination of stereoscopic surface mapping and…
We present a novel algorithm for text-driven image-to-image translation based on a pretrained text-to-image diffusion model. Our method aims to generate a target image by selectively editing the regions of interest in a source image,…
We examine the problem of performing simultaneous and coplanar Particle Image Velocimetry (PIV) and Laser-Induced Fluorescence (LIF) measurements in a stratified fluid initially at rest. Our focus is on enabling detailed velocity and…
Measuring the acoustic characteristics of a space is often done by capturing its impulse response (IR), a representation of how a full-range stimulus sound excites it. This work generates an IR from a single image, which can then be applied…
The remarkable progress in neural-network-driven visual data generation, especially with neural rendering techniques like Neural Radiance Fields and 3D Gaussian splatting, offers a powerful alternative to GANs and diffusion models. These…
We present DiffGaze, a novel method for generating realistic and diverse continuous human gaze sequences on 360{\deg} images based on a conditional score-based denoising diffusion model. Generating human gaze on 360{\deg} images is…
Texture synthesis is a fundamental task in computer vision, whose goal is to generate visually realistic and structurally coherent textures for a wide range of applications, from graphics to scientific simulations. While traditional methods…
Creative image generation has emerged as a compelling area of research, driven by the need to produce novel and high-quality images that expand the boundaries of imagination. In this work, we propose a novel framework for creative…
Diffusion models for single image novel view synthesis (NVS) can generate highly realistic and plausible images, but they are limited in the geometric consistency to the given relative poses. The generated images often show significant…
Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also…
Diffusion Models (DMs) have achieved State-Of-The-Art (SOTA) results in the Lidar point cloud generation task, benefiting from their stable training and iterative refinement during sampling. However, DMs often fail to realistically model…
The capability to detect boulders on the surface of small bodies is beneficial for vision-based applications such as navigation and hazard detection during critical operations. This task is challenging due to the wide assortment of…
Accurately measuring the translations of objects between images is essential in many fields, including biology, medicine, chemistry, and physics. One important application is tracking one or more particles by measuring their apparent…
The identification and removal of systematic errors in object detectors can be a prerequisite for their deployment in safety-critical applications like automated driving and robotics. Such systematic errors can for instance occur under very…
Spacecraft autonomy can be enhanced by vision-based navigation (VBN) techniques. Applications range from manoeuvers around Solar System objects and landing on planetary surfaces, to in-orbit servicing or space debris removal. The…