Related papers: SimWorld: A Unified Benchmark for Simulator-Condit…

This paper introduces UniGen, a novel approach to generating new traffic scenarios for evaluating and improving autonomous driving software through simulation. Our approach models all driving scenario elements in a unified model: the…

Over the past few years there is a growing interest in the learning-based self driving system. To ensure safety, such systems are first developed and validated in simulators before being deployed in the real world. However, most of the…

Rare, yet critical, scenarios pose a significant challenge in testing and evaluating autonomous driving planners. Relying solely on real-world driving scenes requires collecting massive datasets to capture these scenarios. While automatic…

Video generation models have shown strong potential as world models for autonomous driving simulation. However, existing approaches are primarily trained on real-world driving datasets, which mostly contain natural and safe driving…

World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with disparate codebases, data pipelines, and evaluation protocols…

World models have become increasingly popular in acting as learned traffic simulators. Recent work has explored replacing traditional traffic simulators with world models for policy training. In this work, we explore the robustness of…

World models envision potential future states based on various ego actions. They embed extensive knowledge about the driving environment, facilitating safe and scalable autonomous driving. Most existing methods primarily focus on either…

Recent text-to-image models have revolutionized image generation, but they still struggle with maintaining concept consistency across generated images. While existing works focus on character consistency, they often overlook the crucial…

Driving scene generation is a critical domain for autonomous driving, enabling downstream applications, including perception and planning evaluation. Occupancy-centric methods have recently achieved state-of-the-art results by offering…

Autonomous driving promises transformative improvements to transportation, but building systems capable of safely navigating the unstructured complexity of real-world scenarios remains challenging. A critical problem lies in effectively…

World modeling is a crucial task for enabling intelligent agents to effectively interact with humans and operate in dynamic environments. In this work, we propose MineWorld, a real-time interactive world model on Minecraft, an open-ended…

Autonomous driving progress relies on large-scale annotated datasets. In this work, we explore the potential of generative models to produce vast quantities of freely-labeled data for autonomous driving applications and present…

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,…

Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to…

Vision-language models have recently emerged as promising planners for autonomous driving, where success hinges on topology-aware reasoning over spatial structure and dynamic interactions from multimodal input. However, existing models are…

Modeling scenes using video generation models has garnered growing research interest in recent years. However, most existing approaches rely on perspective video models that synthesize only limited observations of a scene, leading to issues…

Novel-view synthesis techniques achieve impressive results for static scenes but struggle when faced with the inconsistencies inherent to casual capture settings: varying illumination, scene motion, and other unintended effects that are…

Safety-critical scenarios are central to evaluating autonomous driving systems, yet their rarity in naturalistic logs makes simulation-based stress testing indispensable. Most scenario generation methods treat surrounding agents as…

Recently, world models have been incorporated into the autonomous driving systems to improve the planning reliability. Existing approaches typically predict future states through appearance generation or deterministic regression, which…

In this paper we describe a learned method of traffic scene generation designed to simulate the output of the perception system of a self-driving car. In our "Scene Diffusion" system, inspired by latent diffusion, we use a novel combination…