Related papers: Scenic: A Language for Scenario Specification and …

Clustering traffic scenarios and detecting novel scenario types are required for scenario-based testing of autonomous vehicles. These tasks benefit from either good similarity measures or good representations for the traffic scenarios. In…

Recently neural scene representations have provided very impressive results for representing 3D scenes visually, however, their study and progress have mainly been limited to visualization of virtual models in computer graphics or scene…

Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted…

Real-world crash reports, which combine textual summaries and sketches, are valuable for scenario-based testing of autonomous driving systems (ADS). However, current methods cannot effectively translate this multimodal data into precise,…

We present a novel deep learning architecture for probabilistic future prediction from video. We predict the future semantics, geometry and motion of complex real-world urban scenes and use this representation to control an autonomous…

Scene Graphs are widely applied in computer vision as a graphical representation of relationships between objects shown in images. However, these applications have not yet reached a practical stage of development owing to biased training…

Scene mining is a subset of image mining in which scenes are classified to a distinct set of classes based on analysis of their content. In other word in scene mining, a label is given to visual content of scene, for example, mountain,…

Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions. Two fundamental limitations of these methods are that most require a full model of the environment…

Adaptation of semantic segmentation networks to different visual conditions is vital for robust perception in autonomous cars and robots. However, previous work has shown that most feature-level adaptation methods, which employ adversarial…

We present a choreographic framework for modelling and analysing concurrent probabilistic systems based on the PRISM model-checker. This is achieved through the development of a choreography language, which is a specification language that…

The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approaches predominantly utilize visual models. However, these…

In target-driven navigation and autonomous exploration, reasonable prediction of unknown regions is crucial for efficient navigation and environment understanding. Existing methods mostly focus on single objects or geometric occupancy maps,…

Iteratively refining and critiquing sketches are crucial steps to developing effective designs. We introduce Scones, a mixed-initiative, machine-learning-driven system that enables users to iteratively author sketches from text…

We introduce SceneDiffuser, a conditional generative model for 3D scene understanding. SceneDiffuser provides a unified model for solving scene-conditioned generation, optimization, and planning. In contrast to prior works, SceneDiffuser is…

Developing deep neural networks to generate 3D scenes is a fundamental problem in neural synthesis with immediate applications in architectural CAD, computer graphics, as well as in generating virtual robot training environments. This task…

This paper focuses on the problem of script identification in unconstrained scenarios. Script identification is an important prerequisite to recognition, and an indispensable condition for automatic text understanding systems designed for…

Systematic testing of autonomous vehicles operating in complex real-world scenarios is a difficult and expensive problem. We present Paracosm, a reactive language for writing test scenarios for autonomous driving systems. Paracosm allows…

When interacting with highly dynamic environments, scene flow allows autonomous systems to reason about the non-rigid motion of multiple independent objects. This is of particular interest in the field of autonomous driving, in which many…

We present an open-source, real-time implementation of SemanticPaint, a system for geometric reconstruction, object-class segmentation and learning of 3D scenes. Using our system, a user can walk into a room wearing a depth camera and a…

Their highly adaptive nature and the combinatorial explosion of possible configurations makes testing context-oriented programs hard. We propose a methodology to automate the generation of test scenarios for developers of feature-based…