Related papers: ConsisDrive: Identity-Preserving Driving World Mod…
Representing diverse and plausible future trajectories is critical for motion forecasting in autonomous driving. However, efficiently capturing these trajectories in a compact set remains challenging. This study introduces a novel approach…
We introduce Consistent Instance Field, a continuous and probabilistic spatio-temporal representation for dynamic scene understanding. Unlike prior methods that rely on discrete tracking or view-dependent features, our approach disentangles…
End-to-end autonomous driving has been recently seen rapid development, exerting a profound influence on both industry and academia. However, the existing work places excessive focus on ego-vehicle status as their sole learning objectives…
Text-to-video (T2V) generation has advanced rapidly, yet maintaining consistent character identities across scenes remains a major challenge. Existing personalization methods often focus on facial identity but fail to preserve broader…
This paper proposes ConsistDreamer - a novel framework that lifts 2D diffusion models with 3D awareness and 3D consistency, thus enabling high-fidelity instruction-guided scene editing. To overcome the fundamental limitation of missing 3D…
Diffusion-based technologies have made significant strides, particularly in personalized and customized facialgeneration. However, existing methods face challenges in achieving high-fidelity and detailed identity (ID)consistency, primarily…
Autonomous driving world models are expected to work effectively across three core dimensions: state, action, and reward. Existing models, however, are typically restricted to limited state modalities, short video sequences, imprecise…
Image instance segmentation is a fundamental research topic in autonomous driving, which is crucial for scene understanding and road safety. Advanced learning-based approaches often rely on the costly 2D mask annotations for training. In…
This report presents a unified technical system addressing the two core capabilities of world models for autonomous driving: world representation and world generation. For world representation, we propose WorldRec, a feed-forward…
Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D representation of the environment, meaning 3D consistency must…
Feature representation via self-supervised learning has reached remarkable success in image-level contrastive learning, which brings impressive performances on image classification tasks. While image-level feature representation mainly…
World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios such as autonomous driving, there commonly exists noncontrollable dynamics independent of the action signals, making it…
In text-to-image models, consistent character generation is the task of achieving text alignment while maintaining the subject's appearance across different prompts. However, since style and appearance are often entangled, the existing…
Predicting the trajectories of surrounding agents is an essential ability for autonomous vehicles navigating through complex traffic scenes. The future trajectories of agents can be inferred using two important cues: the locations and past…
We introduce a wearable driving status recognition device and our open-source dataset, along with a new real-time method robust to changes in lighting conditions for identifying driving status from eye observations of drivers. The core of…
Despite impressive advancements in Autonomous Driving Systems (ADS), navigation in complex road conditions remains a challenging problem. There is considerable evidence that evaluating the subjective risk level of various decisions can…
Egocentric sensors such as AR/VR devices capture human-object interactions and offer the potential to provide task-assistance by recalling 3D locations of objects of interest in the surrounding environment. This capability requires instance…
Closed-loop simulation is essential for advancing end-to-end autonomous driving systems. Contemporary sensor simulation methods, such as NeRF and 3DGS, rely predominantly on conditions closely aligned with training data distributions, which…
Generating long-form storytelling videos with consistent visual narratives remains a significant challenge in video synthesis. We present a novel framework, dataset, and a model that address three critical limitations: background…
The World Health Organization (WHO) reported 1.25 million deaths yearly due to road traffic accidents worldwide and the number has been continuously increasing over the last few years. Nearly fifth of these accidents are caused by…