# MatchFusion: Explicit-Implicit Instance Matching for Spatio-Temporal Multimodal Autonomous Driving

arXiv: https://arxiv.org/abs/2609.25860 · HTML: https://mlsanity.com/paper/2609.25860/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 29 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection](https://mlsanity.com/paper/1711.06396/) (2017)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Driving](https://mlsanity.com/paper/2205.15997/) (2022)
- [TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformers](https://mlsanity.com/paper/2203.11496/) (2022)
- [PointPainting: Sequential Fusion for 3D Object Detection](https://mlsanity.com/paper/1911.10150/) (2019)
- [DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2411.15139/) (2024)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024)
- [DeepInteraction: 3D Object Detection via Modality Interaction](https://mlsanity.com/paper/2208.11112/) (2022)
- [Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Driving](https://mlsanity.com/paper/2503.03125/) (2025)
- [EagerMOT: 3D Multi-Object Tracking via Sensor Fusion](https://mlsanity.com/paper/2104.14682/) (2021)
- [SparseFusion: Fusing Multi-Modal Sparse Representations for Multi-Sensor 3D Object Detection](https://mlsanity.com/paper/2304.14340/) (2023)
- [Sparse4D v3: Advancing End-to-End 3D Detection and Tracking](https://mlsanity.com/paper/2311.11722/) (2023)
- [Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning](https://mlsanity.com/paper/2503.14182/) (2025)
- [Poly-MOT: A Polyhedral Framework For 3D Multi-Object Tracking](https://mlsanity.com/paper/2307.16675/) (2023)
- [MV2DFusion: Leveraging Modality-Specific Object Semantics for Multi-Modal 3D Detection](https://mlsanity.com/paper/2408.05945/) (2024)
- [LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving](https://mlsanity.com/paper/2512.20563/) (2025)
- [ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box](https://mlsanity.com/paper/2303.15334/) (2023)
- [DeepInteraction++: Multi-Modality Interaction for Autonomous Driving](https://mlsanity.com/paper/2408.05075/) (2024)
- [SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras](https://mlsanity.com/paper/2403.10353/) (2024)
- [Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perception](https://mlsanity.com/paper/2512.23635/) (2025)
- [Fusion-Poly: A Polyhedral Framework Based on Spatial-Temporal Fusion for 3D Multi-Object Tracking](https://mlsanity.com/paper/2603.08199/) (2026)

## Abstract (arXiv)

Sparse instance representations provide a compact interface for spatial LiDAR-camera and temporal past-current interaction in multimodal perception and E2EAD. Effective interaction requires reliable instance correspondences despite geometric discrepancies and heterogeneous semantic representations. Attention-based methods exploit contextual semantics but often require specialized representation alignment, increasing computational overhead. In contrast, association based on structured object states is efficient and interpretable but lacks contextual evidence to resolve ambiguous matches. To combine these complementary strengths, we propose MatchFusion, a learnable instance matching and fusion module for spatio-temporal multimodal autonomous driving. MatchFusion initializes pairwise affinities using geometric similarity and category consistency, then selectively refines structurally plausible associations using instance embeddings. The resulting soft matchmap guides a common residual aggregation operator for adaptive information exchange. This unified matching-fusion formulation supports spatial LiDAR-camera and temporal past-current interaction, using multi-view image-plane geometry and motion-compensated BEV geometry as the respective structural priors. Experiments on nuScenes demonstrate consistent perception gains across diverse front-end configurations. Compared with a prior instance-centric fusion method, the MatchFusion-equipped system achieves higher perception accuracy while reducing FLOPs by 55.3% and GPU memory usage by 39.3%, with the matching-fusion module accounting for only 3.7% of total perception latency. Integrating temporal MatchFusion into SparseDrive further improves perception within an E2E framework without additional supervision. These results establish explicit-implicit matching as an effective and efficient mechanism for spatio-temporal instance interaction.