Related papers: PIV/BOS Synthetic Image Generation in Variable Den…
Physics driven image simulation allows for the modeling and creation of realistic imagery beyond what is afforded by typical rendering pipelines. We aim to automatically generate a physically realistic scene for simulation of a given region…
Experimental analysis of cavitation bubble dynamics typically uses optical imaging. However, images are often severely affected by distortions and shadows due to refraction and total reflection at the liquid--gas interface. Here it is shown…
In order to measure the large density-gradient fields of fluids such as underwater shock waves, we employed a fast Fourier demodulation called Fast Checkerboard Demodulation (FCD) method in Background Oriented Schlieren (BOS) technique. BOS…
The pose-guided person image generation task requires synthesizing photorealistic images of humans in arbitrary poses. The existing approaches use generative adversarial networks that do not necessarily maintain realistic textures or need…
Current deep learning approaches in computer vision primarily focus on RGB data sacrificing information. In contrast, RAW images offer richer representation, which is crucial for precise recognition, particularly in challenging conditions…
We explore Bird's-Eye View (BEV) generation, converting a BEV map into its corresponding multi-view street images. Valued for its unified spatial representation aiding multi-sensor fusion, BEV is pivotal for various autonomous driving…
Differentiable particle-based simulation can produce physically plausible motion, but target-driven volumetric shape morphing remains underconstrained: physics-only mass matching captures coarse global structure yet struggles with fine…
Simulating realistic sensors is a challenging part in data generation for autonomous systems, often involving carefully handcrafted sensor design, scene properties, and physics modeling. To alleviate this, we introduce a pipeline for…
Despite recent advances in text-to-image generation, controlling geometric layout and PBR material properties in synthesized scenes remains challenging. We present a pipeline that first produces a G-buffer (albedo, normals, depth,…
The development, benchmarking and validation of aerial Persistent Surveillance (PS) algorithms requires access to specialist Wide Area Aerial Surveillance (WAAS) datasets. Such datasets are difficult to obtain and are often extremely large…
Particle Image Velocimetry (PIV) is the most commonly used optical technique for measuring 2D velocity fields. However, improving the spatial resolution of instantaneous velocity fields and having access to the velocity field in real time…
Background oriented schlieren (BOS) visualization technique is examined by means of optical geometry. Two most important results are the calculation of the sensitivity and spatial resolution of a BOS system, which allows for the…
Ground-to-aerial image synthesis focuses on generating realistic aerial images from corresponding ground street view images while maintaining consistent content layout, simulating a top-down view. The significant viewpoint difference leads…
Quantitative measurements of fluid flow properties can be achieved by background oriented schlieren. In this paper it is shown that this depends on several factors. Image quality index is used to investigate the influence of the image…
Methods for Novel View Synthesis (NVS) have recently found traction in the field of LiDAR simulation and large-scale 3D scene reconstruction. While solutions for faster rendering or handling dynamic scenes have been proposed, LiDAR specific…
We present a novel, easy-to-use method based on the photon-mapping technique to simulate photometric images of moving targets. Realistic images can be created in two passes: photon tracing and image rendering. The nature of light sources,…
Measurement of the velocity field in thermal-hydraulic experiments is of great importance for phenomena interpretation and code validation. Direct measurement employing Particle Image Velocimetry (PIV) is challenging in some multiphase…
Contrary to conventional frame-based imaging, event-based vision (EBV) or dynamic vision sensing (DVS) asynchronously records binary signals of intensity changes for given pixels with microsecond resolution. The present work explores the…
Denoising in the sRGB image space is challenging due to large noise variability. Although end-to-end methods perform well, their effectiveness in real-world scenarios is limited by the scarcity of real noisy-clean image pairs, which are…
3D LiDAR sensors are indispensable for the robust vision of autonomous mobile robots. However, deploying LiDAR-based perception algorithms often fails due to a domain gap from the training environment, such as inconsistent angular…