GenieDrive：面向物理感知驾驶世界模型的4D占用引导视频生成
GenieDrive: Towards Physics-Aware Driving World Model with 4D Occupancy Guided Video Generation
将4D占用作为物理先验引导视频扩散生成，并设计潜变量三平面VAE压缩高分辨率占用，为自动驾驶世界模型提供可复用的物理感知生成框架。
原文依据 Our approach starts by generating 4D occupancy, which serves as a physics-informed foundation for subsequent video generation.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论物理感知的驾驶世界模型对于驾驶规划、分布外数据合成和闭环评估至关重要。然而，现有方法通常依赖单一扩散模型直接将驾驶动作映射到视频，这使得学习困难并导致输出物理不一致。为克服这些挑战，我们提出GenieDrive，一种用于物理感知驾驶视频生成的新框架。我们的方法首先生成4D占用，作为后续视频生成的物理信息基础。4D占用包含丰富的物理信息，包括高分辨率3D结构和动态。为有效压缩这种高分辨率占用，我们提出一种变分自编码器，将占用编码为潜变量三平面表示，将潜变量大小降至先前方法的仅58%。我们进一步引入互控制注意力（MCA）来准确建模控制对占用演化的影响，并以端到端方式联合训练变分自编码器和后续预测模块，以最大化预测精度。这些设计共同在41 FPS的推理速度下实现了预测平均交并比7.2%的提升，同时仅使用3.47 M参数。此外，在视频生成模型中引入归一化多视角注意力，以在我们的4D占用引导下生成多视角驾驶视频，显著提升视频质量，FVD降低20.7%。实验表明，GenieDrive能够实现高度可控、多视角一致且物理感知的驾驶视频生成。
英文原文摘要 1646 字符
Physics-aware driving world model is essential for drive planning, out-of-distribution data synthesis, and closed-loop evaluation. However, existing methods often rely on a single diffusion model to directly map driving actions to videos, which makes learning difficult and leads to physically inconsistent outputs. To overcome these challenges, we propose GenieDrive, a novel framework designed for physics-aware driving video generation. Our approach starts by generating 4D occupancy, which serves as a physics-informed foundation for subsequent video generation. 4D occupancy contains rich physical information, including high-resolution 3D structures and dynamics. To facilitate effective compression of such high-resolution occupancy, we propose a VAE that encodes occupancy into a latent tri-plane representation, reducing the latent size to only 58% of that used in previous methods. We further introduce Mutual Control Attention (MCA) to accurately model the influence of control on occupancy evolution, and we jointly train the VAE and the subsequent prediction module in an end-to-end manner to maximize forecasting accuracy. Together, these designs yield a 7.2% improvement in forecasting mIoU at an inference speed of 41 FPS, while using only 3.47 M parameters. Additionally, a Normalized Multi-View Attention is introduced in the video generation model to generate multi-view driving videos with guidance from our 4D occupancy, significantly improving video quality with a 20.7% reduction in FVD. Experiments demonstrate that GenieDrive enables highly controllable, multi-view consistent, and physics-aware driving video generation.