Related papers: Risk-Controllable Multi-View Diffusion for Driving…

4D driving simulation is essential for developing realistic autonomous driving simulators. Despite advancements in existing methods for generating driving scenes, significant challenges remain in view transformation and spatial-temporal…

We introduce MVControl, a novel neural network architecture that enhances existing pre-trained multi-view 2D diffusion models by incorporating additional input conditions, e.g. edge maps. Our approach enables the generation of controllable…

Recent advances in diffusion models have opened new avenues for research into embodied AI agents and robotics. Despite significant achievements in complex robotic locomotion and skills, mobile manipulation-a capability that requires the…

Motivated by discrete diffusion's success in language-vision modeling, we explore its potential for multi-view generation, a task dominated by continuous approaches. We introduce ViewMask-1-to-3, formulating multi-view synthesis as a…

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…

The creation of diverse and realistic driving scenarios has become essential to enhance perception and planning capabilities of the autonomous driving system. However, generating long-duration, surround-view consistent driving videos…

This paper introduces MVDiffusion, a simple yet effective method for generating consistent multi-view images from text prompts given pixel-to-pixel correspondences (e.g., perspective crops from a panorama or multi-view images given depth…

Route planning for navigation under partial observability plays a crucial role in modern robotics and autonomous driving. Existing route planning approaches can be categorized into two main classes: traditional autoregressive and…

The field of generative models has recently witnessed significant progress, with diffusion models showing remarkable performance in image generation. In light of this success, there is a growing interest in exploring the application of…

Many safety-critical applications, especially in autonomous driving, require reliable object detectors. They can be very effectively assisted by a method to search for and identify potential failures and systematic errors before these…

Existing neural network-based autonomous systems are shown to be vulnerable against adversarial attacks, therefore sophisticated evaluation on their robustness is of great importance. However, evaluating the robustness only under the…

Ensuring the safety and robustness of autonomous driving systems necessitates a comprehensive evaluation in safety-critical scenarios. However, these safety-critical scenarios are rare and difficult to collect from real-world driving data,…

Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…

High-level autonomous driving requires motion planners capable of modeling multimodal future uncertainties while remaining robust in closed-loop interactions. Although diffusion-based planners are effective at modeling complex trajectory…

Diffusion models excel at creating images and videos thanks to their multimodal generative capabilities. These same capabilities have made diffusion models increasingly popular in robotics research, where they are used for generating robot…

Diffusion models, as a class of deep generative models, have recently emerged as powerful tools for robot skills by enabling stable training with reliable convergence. In this paper, we present an end-to-end framework for generating long,…

Urban scene synthesis with video generation models has recently shown great potential for autonomous driving. Existing video generation approaches to autonomous driving primarily focus on RGB video generation and lack the ability to support…

Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models. Generally, incorporating 3D representations into diffusion model decrease the model's speed as well as…

Real-time robotic control demands fast action generation. However, existing generative policies based on diffusion and flow matching require multi-step sampling, fundamentally limiting deployment in time-critical scenarios. We propose…

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…