Related papers: DriveCtrl: Conditioned Sim-to-Real Driving Video G…

In this work, we present CineMaster, a novel framework for 3D-aware and controllable text-to-video generation. Our goal is to empower users with comparable controllability as professional film directors: precise placement of objects within…

Dynamic scene understanding is the ability of a computer system to interpret and make sense of the visual information present in a video of a real-world scene. In this thesis, we present a series of frameworks for dynamic scene…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

Dataset distillation (DD) has emerged as a powerful paradigm for dataset compression, enabling the synthesis of compact surrogate datasets that approximate the training utility of large-scale ones. While significant progress has been…

Simulation is the key to scaling up validation and verification for robotic systems such as autonomous vehicles. Despite advances in high-fidelity physics and sensor simulation, a critical gap remains in simulating realistic behaviors of…

This paper introduces a new framework, DriveBLIP2, built upon the BLIP2-OPT architecture, to generate accurate and contextually relevant explanations for emerging driving scenarios. While existing vision-language models perform well in…

Advances in video generation have significantly improved the realism and quality of created scenes. This has fueled interest in developing intuitive tools that let users leverage video generation as world simulators. Text-to-video (T2V)…

Over the past few years there has been major progress in the field of synthetic data generation using simulation based techniques. These methods use high-end graphics engines and physics-based ray-tracing rendering in order to represent the…

Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail…

High-fidelity and controllable 3D simulation is essential for addressing the long-tail data scarcity in Autonomous Driving (AD), yet existing methods struggle to simultaneously achieve photorealistic rendering and interactive traffic…

Existing dynamic scene generation methods mostly rely on distilling knowledge from pre-trained 3D generative models, which are typically fine-tuned on synthetic object datasets. As a result, the generated scenes are often object-centric and…

Recent advancements in personalized Text-to-Video (T2V) generation have made significant strides in synthesizing character-specific content. However, these methods face a critical limitation: the inability to perform fine-grained control…

Verification and validation of autonomous driving (AD) systems and components is of increasing importance, as such technology increases in real-world prevalence. Safety-critical scenario generation is a key approach to robustify AD policies…

The generation of temporally consistent, high-fidelity driving videos over extended horizons presents a fundamental challenge in autonomous driving world modeling. Existing approaches often suffer from error accumulation and feature…

Instructional video generation is an emerging task that aims to synthesize coherent demonstrations of procedural activities from textual descriptions. Such capability has broad implications for content creation, education, and human-AI…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Accurate monocular depth estimation is a fundamental component of vision-based perception systems in intelligent transportation applications. Despite recent progress, unsupervised monocular approaches still suffer from significant…

Autonomous driving system development is critically dependent on the ability to replay complex and diverse traffic scenarios in simulation. In such scenarios, the ability to accurately simulate the vehicle sensors such as cameras, lidar or…

Despite the substantial progress in deep learning, its adoption in industrial robotics projects remains limited, primarily due to challenges in data acquisition and labeling. Previous sim2real approaches using domain randomization require…

In recent years, AI-assisted IC design methods have demonstrated great potential, but the availability of circuit design data is extremely limited, especially in the public domain. The lack of circuit data has become the primary bottleneck…