Related papers: WinSyn: A High Resolution Testbed for Synthetic Da…
We propose scaling up 3D scene reconstruction by training with synthesized data. At the core of our work is MegaSynth, a procedurally generated 3D dataset comprising 700K scenes - over 50 times larger than the prior real dataset DL3DV -…
Despite considerable efforts to enhance the generalization of 3D pose estimators without costly 3D annotations, existing data augmentation methods struggle in real world scenarios with diverse human appearances and complex poses. We propose…
The availability of real data from areas with high privacy requirements, such as the medical intervention space, is low and the acquisition legally complex. Therefore, this work presents a way to create a synthetic dataset for the medical…
To assist in the development of machine learning methods for automated classification of spectroscopic data, we have generated a universal synthetic dataset that can be used for model validation. This dataset contains artificial spectra…
Learning-based methods for 3D scene reconstruction and object completion require large datasets containing partial scans paired with complete ground-truth geometry. However, acquiring such datasets using real-world scanning systems is…
Synthetic data is being used lately for training deep neural networks in computer vision applications such as object detection, object segmentation and 6D object pose estimation. Domain randomization hereby plays an important role in…
Accurate pain assessment in patients with limited ability to communicate, such as older adults with severe dementia, represents a critical healthcare challenge. Robust automated systems of pain behavior detection may facilitate such…
The state of the art in human-centric computer vision achieves high accuracy and robustness across a diverse range of tasks. The most effective models in this domain have billions of parameters, thus requiring extremely large datasets,…
Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation. Despite these benefits, the efficiency of…
Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their…
The influence of textures on machine learning models has been an ongoing investigation, specifically in texture bias/learning, interpretability, and robustness. However, due to the lack of large and diverse texture data available, the…
Synthetic image datasets offer unmatched advantages for designing and evaluating deep neural networks: they make it possible to (i) render as many data samples as needed, (ii) precisely control each scene and yield granular ground truth…
Synthetic image source attribution is an open challenge, with an increasing number of image generators being released yearly. The complexity and the sheer number of available generative techniques, as well as the scarcity of high-quality…
Single image view synthesis allows for the generation of new views of a scene given a single input image. This is challenging, as it requires comprehensively understanding the 3D scene from a single image. As a result, current methods…
Human head detection, keypoint estimation, and 3D head model fitting are essential tasks with many applications. However, traditional real-world datasets often suffer from bias, privacy, and ethical concerns, and they have been recorded in…
Computer vision technologies markedly enhance the automation capabilities of robotic-assisted minimally invasive surgery (RAMIS) through advanced tool tracking, detection, and localization. However, the limited availability of comprehensive…
Synthetic images created by generative models increase in quality and expressiveness as newer models utilize larger datasets and novel architectures. Although this photorealism is a positive side-effect from a creative standpoint, it…
Transparent objects are common in daily life, and understanding their multi-layer depth information -- perceiving both the transparent surface and the objects behind it -- is crucial for real-world applications that interact with…
Recently, there has been growing interest in developing learning-based methods to detect and utilize salient semi-global or global structures, such as junctions, lines, planes, cuboids, smooth surfaces, and all types of symmetries, for 3D…
Field detection in team sports is an essential task in sports video analysis. However, collecting large-scale and diverse real-world datasets for training detection models is often cost and time-consuming. Synthetic datasets, which allow…