arXiv 2502.169072025-02-24cs.CVcs.AI

MambaFlow：一种新颖的流引导状态空间模型用于场景流估计

MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation

South China Normal University（华南师范大学）；KTH Royal Institute of Technology（瑞典皇家理工学院）；Tongji University（同济大学）

Jiehao Luo, Jintao Cheng, Xiaoyu Tang, Qingwen Zhang, Bohuan Xue, Rui Fan

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出MambaFlow，一种基于Mamba解码器的场景流估计网络，通过流引导全局注意力与场景自适应损失，在Argoverse 2上实现实时最先进性能。

摘要：

场景流估计旨在从连续点云帧中预测三维运动，这在自动驾驶领域具有重要意义。现有方法面临时空建模不足以及体素化过程中细粒度特征固有丢失等挑战。然而，Mamba作为一种具有线性复杂度的全局建模能力的代表性状态空间模型（SSM）的成功，提供了一个有前景的解决方案。在本文中，我们提出了MambaFlow，一种带有基于Mamba的解码器的新颖场景流估计网络。它通过精心设计的骨干网络实现了时空特征的深度交互与耦合。创新性地，我们利用高效的基于Mamba的解码器，以点偏移信息引导基于体素特征的全局注意力建模，学习体素到点的模式，用于将共享体素表示反体素化为逐点特征。为了进一步增强模型在不同场景下的泛化能力，我们提出了一种新颖的场景自适应损失函数，能够自动适应不同的运动模式。在Argoverse 2基准上的大量实验表明，MambaFlow在现有工作中实现了最先进的性能，并具有实时推理速度，能够在真实世界城市场景中实现准确的流估计。代码可在https://github.com/SCNU-RISLAB/MambaFlow获取。

英文摘要：

Scene flow estimation aims to predict 3D motion from consecutive point cloud frames, which is of great interest in autonomous driving field. Existing methods face challenges such as insufficient spatio-temporal modeling and inherent loss of fine-grained feature during voxelization. However, the success of Mamba, a representative state space model (SSM) that enables global modeling with linear complexity, provides a promising solution. In this paper, we propose MambaFlow, a novel scene flow estimation network with a mamba-based decoder. It enables deep interaction and coupling of spatio-temporal features using a well-designed backbone. Innovatively, we steer the global attention modeling of voxel-based features with point offset information using an efficient Mamba-based decoder, learning voxel-to-point patterns that are used to devoxelize shared voxel representations into point-wise features. To further enhance the model's generalization capabilities across diverse scenarios, we propose a novel scene-adaptive loss function that automatically adapts to different motion patterns.Extensive experiments on the Argoverse 2 benchmark demonstrate that MambaFlow achieves state-of-the-art performance with real-time inference speed among existing works, enabling accurate flow estimation in real-world urban scenarios. The code is available at https://github.com/SCNU-RISLAB/MambaFlow.

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。