arXiv 2506.241132025-06-30cs.CV

Epona：用于自动驾驶的自回归扩散世界模型

Epona: Autoregressive Diffusion World Model for Autonomous Driving

Horizon Robotics；Tsinghua University（清华大学）；Peking University（北京大学）；Nanjing University（南京大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）；Nanyang Technological University（南洋理工大学）；Tencent Hunyuan（腾讯文心）

Kaiwen Zhang, Zhenyu Tang, Xiaotao Hu, Xingang Pan, Xiaoyang Guo, Yuan Liu, Jingwei Huang, Li Yuan, Qian Zhang, Xiao-Xiao Long, Xun Cao, Wei Yin

备注：: ICCV2025, Project Page: https://kevin-thu.github.io/Epona/

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出自回归扩散世界模型Epona，通过解耦时空因子分解和模块化轨迹与视频预测，实现高分辨率长时长生成与端到端运动规划，在FVD指标和NAVSIM基准上取得SOTA表现。

摘要：

扩散模型在视频生成中展现出卓越的视觉质量，使其在自动驾驶世界建模中极具前景。然而，现有的基于视频扩散的世界模型在灵活长度、长时程预测以及集成轨迹规划方面存在困难。这是因为传统的视频扩散模型依赖固定长度帧序列的全局联合分布建模，而非在每个时间步顺序构建局部分布。在本研究中，我们提出了Epona，这是一种自回归扩散世界模型，通过两项关键创新实现局部时空分布建模：1）解耦的时空因子分解，将时间动态建模与细粒度的未来世界生成分离开来；2）模块化的轨迹与视频预测，在端到端框架中将运动规划与视觉建模无缝集成。我们的架构支持高分辨率、长时长的生成，同时引入了一种新颖的前向链训练策略，以解决自回归循环中的误差累积问题。实验结果表明，该模型实现了最先进的性能，与先前工作相比，FVD提升了7.4%，预测时长延长了数分钟。学习到的世界模型进一步作为实时运动规划器，在NAVSIM基准上超越了强大的端到端规划器。代码将在https://github.com/Kevin-thu/Epona/公开。

英文摘要：

Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-length, long-horizon predictions and integrating trajectory planning. This is because conventional video diffusion models rely on global joint distribution modeling of fixed-length frame sequences rather than sequentially constructing localized distributions at each timestep. In this work, we propose Epona, an autoregressive diffusion world model that enables localized spatiotemporal distribution modeling through two key innovations: 1) Decoupled spatiotemporal factorization that separates temporal dynamics modeling from fine-grained future world generation, and 2) Modular trajectory and video prediction that seamlessly integrate motion planning with visual modeling in an end-to-end framework. Our architecture enables high-resolution, long-duration generation while introducing a novel chain-of-forward training strategy to address error accumulation in autoregressive loops. Experimental results demonstrate state-of-the-art performance with 7.4\% FVD improvement and minutes longer prediction duration compared to prior works. The learned world model further serves as a real-time motion planner, outperforming strong end-to-end planners on NAVSIM benchmarks. Code will be publicly available at \href{https://github.com/Kevin-thu/Epona/}{https://github.com/Kevin-thu/Epona/}.

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。