# BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving

arXiv: https://arxiv.org/abs/2604.02930 · HTML: https://mlsanity.com/paper/2604.02930/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 36 references that are in the map.
- First posted on arXiv 3 Apr 2026.

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

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation](https://mlsanity.com/paper/2005.04259/) (2020)
- [ST-P3: End-to-end Vision-based Autonomous Driving via Spatial-Temporal Feature Learning](https://mlsanity.com/paper/2207.07601/) (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)
- [BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving](https://mlsanity.com/paper/2205.09743/) (2022)
- [EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention](https://mlsanity.com/paper/2305.07027/) (2023)
- [FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation](https://mlsanity.com/paper/2307.01492/) (2023)
- [SparseBEV: High-Performance Sparse 3D Object Detection from Multi-Camera Videos](https://mlsanity.com/paper/2308.09244/) (2023)
- [FB-BEV: BEV Representation from Forward-Backward View Transformations](https://mlsanity.com/paper/2308.02236/) (2023)
- [End-to-end Contextual Perception and Prediction with Interaction Transformer](https://mlsanity.com/paper/2008.05927/) (2020)
- [A Dynamic Multi-Scale Voxel Flow Network for Video Prediction](https://mlsanity.com/paper/2303.09875/) (2023)
- [StretchBEV: Stretching Future Instance Prediction Spatially and Temporally](https://mlsanity.com/paper/2203.13641/) (2022)
- [PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View](https://mlsanity.com/paper/2306.10761/) (2023)
- [PointBeV: A Sparse Approach to BeV Predictions](https://mlsanity.com/paper/2312.00703/) (2023)
- [CRAT-Pred: Vehicle Trajectory Prediction with Crystal Graph Convolutional Neural Networks and Multi-Head Self-Attention](https://mlsanity.com/paper/2202.04488/) (2022)
- [HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras](https://mlsanity.com/paper/2404.02517/) (2024)
- [DeTra: A Unified Model for Object Detection and Trajectory Forecasting](https://mlsanity.com/paper/2406.04426/) (2024)
- [Exploring Attention GAN for Vehicle Motion Prediction](https://mlsanity.com/paper/2209.12674/) (2022)
- [Video Prediction Transformers without Recurrence or Convolution](https://mlsanity.com/paper/2410.04733/) (2024)
- [Efficient Baselines for Motion Prediction in Autonomous Driving](https://mlsanity.com/paper/2309.03387/) (2023)
- [Fast and Efficient Transformer-based Method for Bird's Eye View Instance Prediction](https://mlsanity.com/paper/2411.06851/) (2024)

## Built on by (most cited first, 1 of 1)

- [TGRIP: A Text-Guided Approach to Vehicle Instance Prediction in Autonomous Driving](https://mlsanity.com/paper/2607.04812/) (2026)

## Abstract (arXiv)

A robust awareness of how dynamic scenes evolve is essential for Autonomous Driving systems, as they must accurately detect, track, and predict the behaviour of surrounding obstacles. Traditional perception pipelines that rely on modular architectures tend to suffer from cumulative errors and latency. Instance Prediction models provide a unified solution, performing Bird's-Eye-View segmentation and motion estimation across current and future frames using information directly obtained from different sensors. However, a key challenge in these models lies in the effective processing of the dense spatial and temporal information inherent in dynamic driving environments. This level of complexity demands architectures capable of capturing fine-grained motion patterns and long-range dependencies without compromising real-time performance. We introduce BEVPredFormer, a novel camera-only architecture for BEV instance prediction that uses attention-based temporal processing to improve temporal and spatial comprehension of the scene and relies on an attention-based 3D projection of the camera information. BEVPredFormer employs a recurrent-free design that incorporates gated transformer layers, divided spatio-temporal attention mechanisms, and multi-scale head tasks. Additionally, we incorporate a difference-guided feature extraction module that enhances temporal representations. Extensive ablation studies validate the effectiveness of each architectural component. When evaluated on the nuScenes dataset, BEVPredFormer was on par or surpassed State-Of-The-Art methods, highlighting its potential for robust and efficient Autonomous Driving perception.