Related papers: Close the Sim2real Gap via Physically-based Struct…

Object perception is fundamental for tasks such as robotic material handling and quality inspection. However, modern supervised deep-learning models require large annotated datasets for robust automation under semi-uncontrolled conditions;…

Being able to reproduce physical phenomena ranging from light interaction to contact mechanics, simulators are becoming increasingly useful in more and more application domains where real-world interaction or labeled data are difficult to…

We propose a novel iterative approach for crossing the reality gap that utilises live robot rollouts and differentiable physics. Our method, RealityGrad, demonstrates for the first time, an efficient sim2real transfer in combination with a…

The lack of labeled datasets in 3D vision for surgical scenes inhibits the development of robust 3D reconstruction algorithms in the medical domain. Despite the popularity of Neural Radiance Fields and 3D Gaussian Splatting in the general…

Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and traditional simulation suffers from a persistent reality gap. While recent generative…

Transferring the depth-based end-to-end policy trained in simulation to physical robots can yield an efficient and robust grasping policy, yet sensor artifacts in real depth maps like voids and noise establish a significant sim2real gap…

Deep reinforcement learning has recently seen huge success across multiple areas in the robotics domain. Owing to the limitations of gathering real-world data, i.e., sample inefficiency and the cost of collecting it, simulation environments…

In this paper we propose a novel approach to generate a synthetic aerial dataset for application in UAV monitoring. We propose to accentuate shape-based object representation by applying texture randomization. A diverse dataset with…

Recent progress in robot learning has been driven by large-scale datasets and powerful visuomotor policy architectures, yet policy robustness remains limited by the substantial cost of collecting diverse demonstrations, particularly for…

Robotic assembly is a longstanding challenge, requiring contact-rich interaction and high precision and accuracy. Many applications also require adaptivity to diverse parts, poses, and environments, as well as low cycle times. In other…

Recent work has focused on generating synthetic imagery to increase the size and variability of training data for learning visual tasks in urban scenes. This includes increasing the occurrence of occlusions or varying environmental and…

Fast and accurate depth sensing has long been a significant research challenge. Event camera, as a device that quickly responds to intensity changes, provides a new solution for structured light (SL) systems. In this paper, we introduce…

Neural implicit representations have been explored to enhance visual SLAM algorithms, especially in providing high-fidelity dense map. Existing methods operate robustly in static scenes but struggle with the disruption caused by moving…

This paper is about effectively utilizing synthetic data for training deep neural networks for industrial parts classification, in particular, by taking into account the domain gap against real-world images. To this end, we introduce a…

Developing robust drone detection systems is often constrained by the limited availability of large-scale annotated training data and the high costs associated with real-world data collection. However, leveraging synthetic data generated…

Object classification with 3D data is an essential component of any scene understanding method. It has gained significant interest in a variety of communities, most notably in robotics and computer graphics. While the advent of deep…

We introduce SceneNet RGB-D, expanding the previous work of SceneNet to enable large scale photorealistic rendering of indoor scene trajectories. It provides pixel-perfect ground truth for scene understanding problems such as semantic…

We introduce neural lithography to address the 'design-to-manufacturing' gap in computational optics. Computational optics with large design degrees of freedom enable advanced functionalities and performance beyond traditional optics.…

Deep Learning has seen an unprecedented increase in vision applications since the publication of large-scale object recognition datasets and introduction of scalable compute hardware. State-of-the-art methods for most vision tasks for…

Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly:…