Related papers: Composing Driving Worlds through Disentangled Cont…

Existing 3D-aware image synthesis approaches mainly focus on generating a single canonical object and show limited capacity in composing a complex scene containing a variety of objects. This work presents DisCoScene: a 3Daware generative…

Generating realistic and diverse road scenarios is essential for autonomous vehicle testing and validation. Nevertheless, owing to the complexity and variability of real-world road environments, creating authentic and varied scenarios for…

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…

High-risk traffic zones such as intersections are a major cause of collisions. This study leverages deep generative models to enhance the safety of autonomous vehicles in an intersection context. We train a 1000-step denoising diffusion…

Audio-driven talking-head generation has advanced rapidly with diffusion-based generative models, yet producing temporally coherent videos with fine-grained motion control remains challenging. We propose DEMO, a flow-matching generative…

Autonomous driving faces critical challenges in rare long-tail events and complex multi-agent interactions, which are scarce in real-world data yet essential for robust safety validation. This paper presents a high-fidelity scenario…

State-of-the-art approaches for autonomous driving integrate multiple sub-tasks of the overall driving task into a single pipeline that can be trained in an end-to-end fashion by passing latent representations between the different modules.…

Recent disentangled representation learning (DRL) methods heavily rely on factor specific strategies-either learning objectives for attributes or model architectures for objects-to embed inductive biases. Such divergent approaches result in…

Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability. This work offers a new generation paradigm that allows flexible control of the output image,…

Learning contextual and spatial environmental representations enhances autonomous vehicle's hazard anticipation and decision-making in complex scenarios. Recent perception systems enhance spatial understanding with sensor fusion but often…

Motion planning is a crucial component in autonomous driving. State-of-the-art motion planners are trained on meticulously curated datasets, which are not only expensive to annotate but also insufficient in capturing rarely seen critical…

Collecting robotic manipulation data is expensive, making it impractical to acquire demonstrations for the combinatorially large space of tasks that arise in multi-object, multi-robot, and multi-environment settings. While recent generative…

Safety validation of autonomous driving systems requires high-risk scenario coverage, clear collision semantics, executable trajectories, and attributable multi-vehicle interactions. Existing safety-critical scenario generation methods…

Real-world autonomous driving, particularly in urban environments with numerous corner cases, requires rigorous testing to ensure product safety and robustness. However, few studies have explored integrating adversarial scenario generation…

Realistic scene reconstruction and view synthesis are essential for advancing autonomous driving systems by simulating safety-critical scenarios. 3D Gaussian Splatting excels in real-time rendering and static scene reconstructions but…

Realistic and diverse multi-agent driving scenes are crucial for evaluating autonomous vehicles, but safety-critical events which are essential for this task are rare and underrepresented in driving datasets. Data-driven scene generation…

Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets. However, generating 3D compositional objects from single images--particularly under occlusions--remains challenging. Existing methods often…

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…

Large-scale labelled driving video data is essential for training autonomous driving systems. Although simulation offers scalable and fully annotated data, the domain gap between synthetic and real-world driving videos significantly limits…

A powerful simulator highly decreases the need for real-world tests when training and evaluating autonomous vehicles. Data-driven simulators flourished with the recent advancement of conditional Generative Adversarial Networks (cGANs),…