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

查看原文 / View Original 编辑 / Edit

Computer Science > Computer Vision and Pattern Recognition arXiv:2610.10759 (cs) [Submitted on 7 Oct 2026] Title: MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting Authors: Jiuming Liu, Jianing Li, Mengmeng Liu, Hongyang He, Hesheng Wang, Per Ola Kristensson.

计算机科学 > 计算机视觉与模式识别 arXiv:2610.10759 (cs) [提交于 2026 年 10 月 7 日] 标题：MESSENGER：通过自回归下一帧预测实现记忆增强的序列场景流估计作者：Jiuming Liu, Jianing Li, Mengmeng Liu, Hongyang He, Hesheng Wang, Per Ola Kristensson。

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.

摘要：场景流可以捕捉动态场景中的底层 3D 运动位移。早期依赖瞬时两帧运动的成对估计器缺乏长期时间相关性，且在未来预测的外推能力方面表现不佳。尽管一些近期方法尝试以序列到序列的方式探索多帧场景流估计，但它们通常会随着输入帧数的增加而面临沉重的计算开销，并因运动传播效率低下而导致长程预测性能下降。

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.

为了解决这些问题，我们提出了一种名为 MESSENGER 的新型记忆增强序列场景流流水线。为了充分挖掘连续序列中自然存在的长期时间依赖性，我们设计了一个记忆缓冲区，通过显式存储多个历史流估计值和潜在状态来实现。对于每一帧输入，系统会关联并检索时间上存储的流和状态，以自回归的下一帧预测方式预测当前的初始流。

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.

此外，我们开发了一个不确定性感知重加权模块，用于过滤不可靠的检索结果并减轻累积误差。在 nuScenes 和 Argoverse 2 上进行的广泛实验证明了 MESSENGER 的最先进性能，在长程未来外推中，nuScenes 上的 EPE3D 降低了 71.6%，Argoverse 2 上降低了 67.7%。这种优越性归功于我们设计的自回归预测范式，它自然地促使网络基于历史观测结果逐步学习下一帧的分布。