# Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception

arXiv: https://arxiv.org/abs/2303.05970 · HTML: https://mlsanity.com/paper/2303.05970/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 71 references that are in the map.
- First posted on arXiv 10 Mar 2023.

## Builds on (most cited first, 30 of 61)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [FCOS: Fully Convolutional One-Stage Object Detection](https://mlsanity.com/paper/1904.01355/) (2019)
- [Spatial Transformer Networks](https://mlsanity.com/paper/1506.02025/) (2015)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [Multi-View 3D Object Detection Network for Autonomous Driving](https://mlsanity.com/paper/1611.07759/) (2016)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection](https://mlsanity.com/paper/2104.10956/) (2021)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Net](https://mlsanity.com/paper/2012.12395/) (2020)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)

## Built on by (most cited first, 30 of 65)

- [StreamMapNet: Streaming Mapping Network for Vectorized Online HD Map Construction](https://mlsanity.com/paper/2308.12570/) (2023)
- [DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation](https://mlsanity.com/paper/2406.16855/) (2024)
- [Sparse4D v2: Recurrent Temporal Fusion with Sparse Model](https://mlsanity.com/paper/2305.14018/) (2023)
- [Sparse4D v3: Advancing End-to-End 3D Detection and Tracking](https://mlsanity.com/paper/2311.11722/) (2023)
- [MapTracker: Tracking with Strided Memory Fusion for Consistent Vector HD Mapping](https://mlsanity.com/paper/2403.15951/) (2024)
- [HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction](https://mlsanity.com/paper/2403.08639/) (2024)
- [SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving](https://mlsanity.com/paper/2404.06892/) (2024)
- [Stream Query Denoising for Vectorized HD Map Construction](https://mlsanity.com/paper/2401.09112/) (2024)
- [Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving](https://mlsanity.com/paper/2405.17426/) (2024)
- [BEVNeXt: Reviving Dense BEV Frameworks for 3D Object Detection](https://mlsanity.com/paper/2312.01696/) (2023)
- [UniWorld: Autonomous Driving Pre-training via World Models](https://mlsanity.com/paper/2308.07234/) (2023)
- [SparseLIF: High-Performance Sparse LiDAR-Camera Fusion for 3D Object Detection](https://mlsanity.com/paper/2403.07284/) (2024)
- [PointBeV: A Sparse Approach to BeV Predictions](https://mlsanity.com/paper/2312.00703/) (2023)
- [RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion](https://mlsanity.com/paper/2412.12725/) (2024)
- [MachMap: End-to-End Vectorized Solution for Compact HD-Map Construction](https://mlsanity.com/paper/2306.10301/) (2023)
- [UniScene: Multi-Camera Unified Pre-training via 3D Scene Reconstruction for Autonomous Driving](https://mlsanity.com/paper/2305.18829/) (2023)
- [Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection](https://mlsanity.com/paper/2310.15670/) (2023)
- [PrevPredMap: Exploring Temporal Modeling with Previous Predictions for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2407.17378/) (2024)
- [GeoBEV: Learning Geometric BEV Representation for Multi-view 3D Object Detection](https://mlsanity.com/paper/2409.01816/) (2024)
- [OCBEV: Object-Centric BEV Transformer for Multi-View 3D Object Detection](https://mlsanity.com/paper/2306.01738/) (2023)
- [SimPB: A Single Model for 2D and 3D Object Detection from Multiple Cameras](https://mlsanity.com/paper/2403.10353/) (2024)
- [MemFusionMap: Working Memory Fusion for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2409.18737/) (2024)
- [Rethinking Temporal Fusion with a Unified Gradient Descent View for 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2504.12959/) (2025)
- [Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking](https://mlsanity.com/paper/2510.10287/) (2025)
- [Lift-Attend-Splat: Bird's-eye-view camera-lidar fusion using transformers](https://mlsanity.com/paper/2312.14919/) (2023)
- [MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning](https://mlsanity.com/paper/2403.08760/) (2024)
- [SparseFusion: Efficient Sparse Multi-Modal Fusion Framework for Long-Range 3D Perception](https://mlsanity.com/paper/2403.10036/) (2024)
- [HisTrackMap: Global Vectorized High-Definition Map Construction via History Map Tracking](https://mlsanity.com/paper/2503.07168/) (2025)
- [MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations](https://mlsanity.com/paper/2503.13858/) (2025)
- [InteractionMap: Improving Online Vectorized HDMap Construction with Interaction](https://mlsanity.com/paper/2503.21659/) (2025)

## Abstract (arXiv)

Long-term temporal fusion is a crucial but often overlooked technique in camera-based Bird's-Eye-View (BEV) 3D perception. Existing methods are mostly in a parallel manner. While parallel fusion can benefit from long-term information, it suffers from increasing computational and memory overheads as the fusion window size grows. Alternatively, BEVFormer adopts a recurrent fusion pipeline so that history information can be efficiently integrated, yet it fails to benefit from longer temporal frames. In this paper, we explore an embarrassingly simple long-term recurrent fusion strategy built upon the LSS-based methods and find it already able to enjoy the merits from both sides, i.e., rich long-term information and efficient fusion pipeline. A temporal embedding module is further proposed to improve the model's robustness against occasionally missed frames in practical scenarios. We name this simple but effective fusing pipeline VideoBEV. Experimental results on the nuScenes benchmark show that VideoBEV obtains strong performance on various camera-based 3D perception tasks, including object detection (55.4% mAP and 62.9% NDS), segmentation (48.6% vehicle mIoU), tracking (54.8% AMOTA), and motion prediction (0.80m minADE and 0.463 EPA).