Related papers: The GOOSE Dataset for Perception in Unstructured E…
In this paper, we present a synthesis pipeline and dataset for training / testing data in the task of traffic sign recognition that combines the advantages of data-driven and analytical modeling: GAN-based texture generation enables…
Automation of complex traffic scenarios is expected to rely on input from a roadside infrastructure to complement the vehicles' environment perception. We here explore design requirements for a prototypical setup of virtual vision or RADAR…
Safe highway autonomy for heavy trucks remains an open and unsolved challenge: due to long braking distances, scene understanding of hundreds of meters is required for anticipatory planning and to allow safe braking margins. However,…
We present semi-supervised deep learning approaches for traversability estimation from fisheye images. Our method, GONet, and the proposed extensions leverage Generative Adversarial Networks (GANs) to effectively predict whether the area…
The ability to estimate pose and generate maps using 3D LiDAR significantly enhances robotic system autonomy. However, existing open-source datasets lack representation of geometrically degenerate environments, limiting the development and…
Automated 3D city generation, focusing on road networks and building layouts, is in high demand for applications in urban design, multimedia games and autonomous driving simulations. The surge of generative AI facilitates designing city…
Deep learning for detecting objects in remotely sensed imagery can enable new technologies for important applications including mitigating climate change. However, these models often require large datasets labeled with bounding box…
This work tackles scene understanding for outdoor robotic navigation, solely relying on images captured by an on-board camera. Conventional visual scene understanding interprets the environment based on specific descriptive categories.…
Drone-view geo-localization aims to match a query drone image, often captured under adverse weather conditions (e.g., rain, snow, fog), against a gallery of geo-tagged satellite images. Weather-induced degradations in the drone view, such…
Generalization of imitation-learned navigation policies to environments unseen in training remains a major challenge. We address this by conducting the first large-scale study of how data quantity and data diversity affect real-world…
Autonomous aerial navigation in dense natural environments remains challenging due to limited visibility, thin and irregular obstacles, GNSS-denied operation, and frequent perceptual degradation. This work presents an improved deep…
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…
One of the most fundamental and information-laden actions humans do is to look at objects. However, a survey of current works reveals that existing gaze-related datasets annotate only the pixel being looked at, and not the boundaries of a…
Standard training datasets for deep learning often contain objects in common settings (e.g., "a horse on grass" or "a ship in water") since they are usually collected by randomly scraping the web. Uncommon and rare settings (e.g., "a plane…
We introduce DIODE, a dataset that contains thousands of diverse high resolution color images with accurate, dense, long-range depth measurements. DIODE (Dense Indoor/Outdoor DEpth) is the first public dataset to include RGBD images of…
Depth estimation is an essential task toward full scene understanding since it allows the projection of rich semantic information captured by cameras into 3D space. While the field has gained much attention recently, datasets for depth…
In this paper, we present and study a new image segmentation task, called Generalized Open-set Semantic Segmentation (GOSS). Previously, with the well-known open-set semantic segmentation (OSS), the intelligent agent only detects the…
Inner-city intersections are among the most critical traffic areas for injury and fatal accidents. Automated vehicles struggle with the complex and hectic everyday life within those areas. Sensor-equipped smart infrastructures, which can…
Collaborative perception has attracted growing interest from academia and industry due to its potential to enhance perception accuracy, safety, and robustness in autonomous driving through multi-agent information fusion. With the…
Interacting with the world is a multi-sensory experience: achieving effective general-purpose interaction requires making use of all available modalities -- including vision, touch, and audio -- to fill in gaps from partial observation. For…