具身开发者社区

外观

论文arXiv 2610.1075921 天前

MESSENGER：通过自回归下一帧预测的记忆增强序列场景流估计 ​

MESSENGER用记忆缓冲与自回归下一帧预测解决序列场景流长时依赖和外推问题，并在nuScenes、Argoverse 2验证。

AI 整理
  • 本体 SDK 与控制
  • 具身模型

原文链接：MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting（arXiv 2610.10759 · 发布日期：2026-10-07）

MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting

MESSENGER用记忆缓冲与自回归下一帧预测解决序列场景流长时依赖和外推问题，并在nuScenes、Argoverse 2验证。

核心要点 ​

  • 两帧估计缺乏长期时间相关性，多帧方法计算开销大且长时预测易退化。
  • 方法显式存储历史场景流估计和潜在状态，并检索相关信息预测当前初始化流。
  • 不确定性感知重加权模块过滤不可靠检索，缓解自回归传播中的累积误差。
  • 在nuScenes和Argoverse 2上达到SOTA，长时未来外推EPE3D分别降低71.6%和67.7%；代码将发布。

验证范围与局限：验证范围限于nuScenes和Argoverse 2上的长时域未来外推实验。

英文摘要 (Abstract) ​

Scene flow can capture low-level 3D motion displacements in dynamic scenarios. Early pairwise estimators relying on instantaneous two-frame motion lack long-term temporal correlation and also struggle with poor extrapolation ability in future prediction. Although some recent methods attempt to explore multi-frame scene flow estimation in a sequence-to-sequence manner, they typically suffer from heavy computational overhead with increasing input frames and long-horizon prediction degradation due to ineffective motion propagation. To address these problems, we propose a novel memory-enhanced sequential scene flow pipeline, called MESSENGER. To sufficiently mine long-term temporal dependencies naturally within consecutive sequences, a memory buffer is designed by explicitly storing multiple history flow estimates and latent states. For each input frame, the temporally stored flows and states are correlated and retrieved to predict the current initialized flow in a next-frame forecasting manner. Furthermore, we develop an uncertainty-aware reweighting module to filter unreliable retrievals and mitigate accumulated errors. Extensive experiments on nuScenes and Argoverse 2 demonstrate state-of-the-art performance of our MESSENGER, reducing EPE3D by 71.6% on nuScenes and 67.7% on Argoverse 2 in long-horizon future extrapolation. This superiority can be attributed to our designed autoregressive forecasting paradigm, which naturally forces the network to progressively learn the next-frame distribution based on history observations. Code will be released at https://github.com/liujiuming123/Messenger.

作者：Jiuming Liu, Jianing Li, Mengmeng Liu, Hongyang He, Hesheng Wang, Per Ola Kristensson

来源

本页事实对应的公开页面，以原文为准。

  1. arXiv 2610.10759：MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting访问 2026-10-21