D$^2$-World：通过解耦动态流实现的高效世界模型
D$^2$-World: An Efficient World Model through Decoupled Dynamic Flow
AI总结：
针对CVPR-2024自主系统基础模型研讨会的预测世界模型挑战赛，提出通过解耦动态流预测未来点云的D$^2$-World模型，以非自回归方式生成未来占据，在OpenScene基准获亚军且训练速度快300%以上。
摘要：
本技术报告总结了CVPR-2024自主系统基础模型研讨会上举办的预测世界模型挑战赛的亚军解决方案。我们提出D$^2$-World，这是一种新颖的世界模型，可通过解耦动态流有效预测未来点云。具体而言，过去的语义占据通过现有占据网络（如BEVDet）获取。随后，占据结果作为单阶段世界模型的输入，以非自回归方式生成未来占据。为进一步简化任务，世界模型中执行动态体素解耦：模型通过体素流扭曲现有观测生成未来动态体素，而静态体素可通过姿态变换轻松获取。该方法在OpenScene预测世界模型基准上达到最先进性能并获得亚军，训练速度比基线模型快300%以上。代码可在https://github.com/zhanghm1995/D2-World获取。
英文摘要：
This technical report summarizes the second-place solution for the Predictive World Model Challenge held at the CVPR-2024 Workshop on Foundation Models for Autonomous Systems. We introduce D$^2$-World, a novel World model that effectively forecasts future point clouds through Decoupled Dynamic flow. Specifically, the past semantic occupancies are obtained via existing occupancy networks (e.g., BEVDet). Following this, the occupancy results serve as the input for a single-stage world model, generating future occupancy in a non-autoregressive manner. To further simplify the task, dynamic voxel decoupling is performed in the world model. The model generates future dynamic voxels by warping the existing observations through voxel flow, while remaining static voxels can be easily obtained through pose transformation. As a result, our approach achieves state-of-the-art performance on the OpenScene Predictive World Model benchmark, securing second place, and trains more than 300% faster than the baseline model. Code is available at https://github.com/zhanghm1995/D2-World.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
