MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910842443792384 |
|---|---|
| author | Luo, Jiehao Cheng, Jintao Tang, Xiaoyu Zhang, Qingwen Xue, Bohuan Fan, Rui |
| author_facet | Luo, Jiehao Cheng, Jintao Tang, Xiaoyu Zhang, Qingwen Xue, Bohuan Fan, Rui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_16907 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation Luo, Jiehao Cheng, Jintao Tang, Xiaoyu Zhang, Qingwen Xue, Bohuan Fan, Rui Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | MambaFlow: A Novel and Flow-guided State Space Model for Scene Flow Estimation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2502.16907 |