StreamVLO: Streaming Visual-LiDAR Odometry with Cumulative Drift Compensation
Mengmeng Liu, Jiuming Liu, Michael Ying Yang, Chaokang Jiang, Jiangtao Li, Yunpeng Zhang, Hesheng Wang, Francesco Nex, Hao Cheng
Abstract
We propose StreamVLO, a streaming visual-LiDAR odometry framework that performs unified spatio-temporal correlation with Mamba models and tackles the long-standing cumulative drift problem via an online Cumulative Drift Compensation scheme for localization in 4D dynamic environments. Specifically, StreamVLO introduces a unified spatio-temporal correlation module built on Mamba to fuse heterogeneous visual and LiDAR cues across multiframe clips, overcoming the limited temporal exploration of prior pairwise methods. Furthermore, a Cumulative Drift Compensation module minimizes cumulative drift by iteratively learning residual corrections from multiple historical frames in a causal manner. To strengthen spatial feature representation on salient regions, we adopt a Keypoint-Aware Auxiliary Loss with a winner-takes-all strategy. StreamVLO achieves state-of-the-art performance on two commonly used autonomous driving datasets, reducing errors by 19% (t rel ) and 22% (r rel ) on KITTI, and by 18% ATE and 16% RPE on Argoverse, while remaining suitable for real-time deployment.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- VMamba: Visual State Space Model cites Efficiently Modeling Long Sequences with Structured State Spaces
- VMamba: Visual State Space Model cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- VMamba: Visual State Space Model cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
- Efficiently Modeling Long Sequences with Structured State Spaces cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- Swin Transformer: Hierarchical Vision Transformer using Shifted Windows cites Deformable DETR: Deformable Transformers for End-to-End Object Detection
Builds on31
- Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
- An Image is Worth 16x16 Words: Transformers for Image Recognition at ScaleAlexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn et al.ICLR 2021 · 21,477 citations
- Deformable DETR: Deformable Transformers for End-to-End Object DetectionXizhou Zhu, Weijie Su, Lewei Lu, Bin Li et al.ICLR 2021 · 7,353 citations
- Efficiently Modeling Long Sequences with Structured State SpacesAlbert Gu, Karan Goel, Christopher RéICLR 2022 · 3,482 citations
- VMamba: Visual State Space ModelYue Liu, Yunjie Tian, Yuzhong Zhao, Hongtian Yu et al.NeurIPS 2024 · 3,199 citations
Related papers
- OpenVO: Open-World Visual Odometry with Temporal Dynamics AwarenessPhuc Nguyen, Anh N Nhu, Ming C. LinCVPR 2026 · 2 citations
- UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object DetectionXin Jin, Haisheng Su, Kai Liu, Cong Ma et al.CVPR 2025
- R4Det: 4D Radar-Camera Fusion for High-Performance 3D Object DetectionZhongyu Xia, Yousen Tang, Yongtao Wang, Zhifeng Wang et al.CVPR 2026 · 4 citations
- Real-time Object Detection for Streaming PerceptionJinrong Yang, Songtao Liu, Zeming Li, Xiaoping Li et al.CVPR 2022 · 61 citations
- RCP-LO: A Relative Coordinate Prediction Framework for Generalizable Deep LiDAR OdometryChen Liu, Wen Li, Yongshu Huang, Minghang Zhu et al.AAAI 2026
