Related papers: OmniGen: Unified Multimodal Sensor Generation for …

Recent advancements in driving world models enable controllable generation of high-quality RGB videos or multimodal videos. Existing methods primarily focus on metrics related to generation quality and controllability. However, they often…

Perception robustness under adverse weather remains a critical challenge for autonomous driving, with the core bottleneck being the scarcity of real-world video data in adverse weather. Existing weather generation approaches struggle to…

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…

Rapid generation of large-scale orthoimages from Unmanned Aerial Vehicles (UAVs) has been a long-standing focus of research in the field of aerial mapping. A multi-sensor UAV system, integrating the Global Positioning System (GPS), Inertial…

Vision-Language Models(VLMs) excel at autoregressive text generation, yet end-to-end autonomous driving requires multi-task learning with structured outputs and heterogeneous decoding behaviors, such as autoregressive language generation,…

Unified multimodal models aim to jointly enable visual understanding and generation, yet current benchmarks rarely examine their true integration. Existing evaluations either treat the two abilities in isolation or overlook tasks that…

Unifying multimodal understanding and generation has shown impressive capabilities in cutting-edge proprietary systems. In this work, we introduce BAGEL, an open-source foundational model that natively supports multimodal understanding and…

The field of autonomous driving increasingly demands high-quality annotated training data. In this paper, we propose Panacea, an innovative approach to generate panoramic and controllable videos in driving scenarios, capable of yielding an…

Driving video generation has achieved much progress in controllability, video resolution, and length, but fails to support fine-grained object-level controllability for diverse driving videos, while preserving the spatiotemporal…

We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while…

Autonomous driving requires an understanding of the static environment from sensor data. Learned Bird's-Eye View (BEV) encoders are commonly used to fuse multiple inputs, and a vector decoder predicts a vectorized map representation from…

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…

LiDAR scene generation is increasingly important for scalable simulation and synthetic data creation, especially under diverse sensing conditions that are costly to capture at scale. Typically, diffusion-based LiDAR generators are developed…

3D Human motion generation is pivotal across film, animation, gaming, and embodied intelligence. Traditional 3D motion synthesis relies on costly motion capture, while recent work shows that 2D videos provide rich, temporally coherent…

$360^{\circ}$ omnidirectional images (ODIs) have gained considerable attention recently, and are widely used in various virtual reality (VR) and augmented reality (AR) applications. However, capturing such images is expensive and requires…

The past few years have witnessed the rapid development of vision-centric 3D perception in autonomous driving. Although the 3D perception models share many structural and conceptual similarities, there still exist gaps in their feature…

As autonomous driving technology matures, end-to-end methodologies have emerged as a leading strategy, promising seamless integration from perception to control via deep learning. However, existing systems grapple with challenges such as…

Perception is essential for autonomous driving system. Recent approaches based on Bird's-eye-view (BEV) and deep learning have made significant progress. However, there exists challenging issues including lengthy development cycles, poor…

During the process of driving, humans usually rely on multiple senses to gather information and make decisions. Analogously, in order to achieve embodied intelligence in autonomous driving, it is essential to integrate multidimensional…

Generating multi-view videos for autonomous driving training has recently gained much attention, with the challenge of addressing both cross-view and cross-frame consistency. Existing methods typically apply decoupled attention mechanisms…