Related papers: ScenarioControl: Vision-Language Controllable Vect…

With the rapid advancement of autonomous driving technology, a lack of data has become a major obstacle to enhancing perception model accuracy. Researchers are now exploring controllable data generation using world models to diversify…

Roundabouts, characterized by frequent merging and yielding interactions, remain a safety-critical corner case for the development and testing of intelligent driving functions. However, extracting sufficient near-critical scenarios from…

Model-based control is a popular paradigm for robot navigation because it can leverage a known dynamics model to efficiently plan robust robot trajectories. However, it is challenging to use model-based methods in settings where the…

We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike methods conditioned on a single image or a short clip, we…

Controllable 3D scene generation has extensive applications in virtual reality and interior design, where the generated scenes should exhibit high levels of realism and controllability in terms of geometry. Scene graphs provide a suitable…

Videos express highly structured spatio-temporal patterns of visual data. A video can be thought of as being governed by two factors: (i) temporally invariant (e.g., person identity), or slowly varying (e.g., activity), attribute-induced…

Autonomous driving systems require comprehensive evaluation in safety-critical scenarios to ensure safety and robustness. However, such scenarios are rare and difficult to collect from real-world driving data, necessitating simulation-based…

Safely interacting with humans is a significant challenge for autonomous driving. The performance of this interaction depends on machine learning-based modules of an autopilot, such as perception, behavior prediction, and planning. These…

Long-tail and rare event problems become crucial when autonomous driving algorithms are applied in the real world. For the purpose of evaluating systems in challenging settings, we propose a generative framework to create safety-critical…

Safety-critical traffic simulation plays a crucial role in evaluating autonomous driving systems under rare and challenging scenarios. However, existing approaches often generate unrealistic scenarios due to insufficient consideration of…

Generating realistic robotic manipulation videos is an important step toward unifying perception, planning, and action in embodied agents. While existing video diffusion models require large domain-specific datasets and struggle to…

Video generation is one of the most challenging tasks in Machine Learning and Computer Vision fields of study. In this paper, we tackle the text to video generation problem, which is a conditional form of video generation. Humans can…

Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the 3D object layout. However, those models are trained on…

This work addresses on the following problem: given a set of unsynchronized history observations of two scenes that are correlative on their dynamic changes, the purpose is to learn a cross-scene predictor, so that with the observation of…

Generating high-fidelity and controllable synthetic data is critical for advancing end-to-end autonomous driving, particularly for addressing the long tail of rare safety-critical scenarios. Existing occupancy-guided methods typically rely…

Video diffusion techniques have advanced significantly in recent years; however, they struggle to generate realistic imagery of car crashes due to the scarcity of accident events in most driving datasets. Improving traffic safety requires…

We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene synthesis either…

Autonomous driving promises safer roads, reduced congestion, and improved mobility, yet validating these systems across diverse conditions remains a major challenge. Real-world testing is expensive, time-consuming, and sometimes unsafe,…

We advocate the idea of the natural-language-driven(NLD) simulation to efficiently produce the object interactions between multiple objects in the virtual road scenes, for teaching and testing the autonomous driving systems that should take…

Synthesizing interactive 3D scenes from text is essential for gaming, virtual reality, and embodied AI. However, existing methods face several challenges. Learning-based approaches depend on small-scale indoor datasets, limiting the scene…