分离动态流，高效预测未来点云，训练速度超基线3倍以上。
D$^2$-World: An Efficient World Model through Decoupled Dynamic Flow
- 通过解耦动态与静态体素，分步预测未来场景
- 在OpenScene基准上达最优性能，训练速度快3倍以上
- 适合自动驾驶场景建模与实时预测研究者
本文总结了在CVPR-2024自主系统基础模型研讨会上的预测世界模型挑战赛第二名解决方案。我们提出D²-World，一种基于解耦动态流的新世界模型，可高效预测未来点云。首先利用现有占用网络（如BEVDet）获取历史语义占用信息，随后输入单阶段世界模型，以非自回归方式生成未来占用。为简化任务，世界模型中引入动态体素解耦：通过体素流对现有观测进行形变，生成未来动态体素；静态体素则通过位姿变换直接获得。该方法在OpenScene预测世界模型基准上取得领先性能，获第二名，并实现比基线模型快300%以上的训练速度。代码已开源：https://github.com/zhanghm1995/D2-World。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。