Related papers: GenieDrive: Towards Physics-Aware Driving World Mo…
Trajectory generation and prediction are two interwoven tasks that play important roles in planner evaluation and decision making for intelligent vehicles. Most existing methods focus on one of the two and are optimized to directly output…
Recent advances in 4D generation mainly focus on generating 4D content by distilling pre-trained text or single-view image-conditioned models. It is inconvenient for them to take advantage of various off-the-shelf 3D assets with multi-view…
Recent progress in driving video generation has shown significant potential for enhancing self-driving systems by providing scalable and controllable training data. Although pretrained state-of-the-art generation models, guided by 2D layout…
World models, especially in autonomous driving, are trending and drawing extensive attention due to their capacity for comprehending driving environments. The established world model holds immense potential for the generation of…
Physical awareness, especially in a large and dynamic environment, is shaped by sensing decisions that determine observability across space, time, and scale, while observations impact the quality of sensing decisions. This loopy information…
Understanding the dynamic physical world, characterized by its evolving 3D structure, real-world motion, and semantic content with textual descriptions, is crucial for human-agent interaction and enables embodied agents to perceive and act…
End-to-End autonomous driving (E2E-AD) has emerged as a new paradigm, where trajectory planning plays a crucial role. Existing studies mainly follow two directions: trajectory generation oriented, which focuses on producing high-quality…
Understanding how the 3D scene evolves is vital for making decisions in autonomous driving. Most existing methods achieve this by predicting the movements of object boxes, which cannot capture more fine-grained scene information. In this…
Accurate perception of the dynamic environment is a fundamental task for autonomous driving and robot systems. This paper introduces Let Occ Flow, the first self-supervised work for joint 3D occupancy and occupancy flow prediction using…
Generalization is a central challenge in autonomous driving, as real-world deployment requires robust performance under unseen scenarios, sensor domains, and environmental conditions. Recent world-model-based planning methods have shown…
Recent video diffusion models generate photorealistic, temporally coherent videos, yet they fall short as reliable world models for autonomous driving, where structured motion and physically consistent interactions are essential. Adapting…
Autonomous driving is an emerging technology that is expected to bring significant social, economic, and environmental benefits. However, these benefits come with rising energy consumption by computation engines, limiting the driving range…
In this work we aim to predict the driver's focus of attention. The goal is to estimate what a person would pay attention to while driving, and which part of the scene around the vehicle is more critical for the task. To this end we propose…
Video Generation Models (VGMs) have become powerful backbones for Vision-Language-Action (VLA) models, leveraging large-scale pretraining for robust dynamics modeling. However, current methods underutilize their distribution modeling…
By sharing information across multiple agents, collaborative perception helps autonomous vehicles mitigate occlusions and improve overall perception accuracy. While most previous work focus on vehicle-to-vehicle and…
We present UniFuture, a unified 4D Driving World Model designed to simulate the dynamic evolution of the 3D physical world. Unlike existing driving world models that focus solely on 2D pixel-level video generation (lacking geometry) or…
World models for autonomous driving have the potential to dramatically improve the reasoning capabilities of today's systems. However, most works focus on camera data, with only a few that leverage lidar data or combine both to better…
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…
Automated driving fundamentally requires knowledge about the surrounding geometry of the scene. Modern approaches use only captured images to predict occupancy maps that represent the geometry. Training these approaches requires accurate…
3D occupancy perception holds a pivotal role in recent vision-centric autonomous driving systems by converting surround-view images into integrated geometric and semantic representations within dense 3D grids. Nevertheless, current models…