# PowerBEV: A Powerful Yet Lightweight Framework for Instance Prediction in Bird's-Eye View

arXiv: https://arxiv.org/abs/2306.10761 · HTML: https://mlsanity.com/paper/2306.10761/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 45 references that are in the map.
- First posted on arXiv 19 Jun 2023.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [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)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [MultiPath: Multiple Probabilistic Anchor Trajectory Hypotheses for Behavior Prediction](https://mlsanity.com/paper/1910.05449/) (2019)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Panoptic-DeepLab](https://mlsanity.com/paper/1910.04751/) (2019)
- [PIXOR: Real-time 3D Object Detection from Point Clouds](https://mlsanity.com/paper/1902.06326/) (2019)
- [BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection](https://mlsanity.com/paper/2203.17054/) (2022)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [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)
- [MP3: A Unified Model to Map, Perceive, Predict and Plan](https://mlsanity.com/paper/2101.06806/) (2021)
- [BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving](https://mlsanity.com/paper/2205.09743/) (2022)
- [IntentNet: Learning to Predict Intention from Raw Sensor Data](https://mlsanity.com/paper/2101.07907/) (2021)
- [PolarFormer: Multi-camera 3D Object Detection with Polar Transformer](https://mlsanity.com/paper/2206.15398/) (2022)
- [PnPNet: End-to-End Perception and Prediction with Tracking in the Loop](https://mlsanity.com/paper/2005.14711/) (2020)
- [BEVSegFormer: Bird's Eye View Semantic Segmentation From Arbitrary Camera Rigs](https://mlsanity.com/paper/2203.04050/) (2022)
- [Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions](https://mlsanity.com/paper/1906.08945/) (2019)
- [Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Data](https://mlsanity.com/paper/1910.08233/) (2019)
- [MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps](https://mlsanity.com/paper/2003.06754/) (2020)

## Built on by (most cited first, 24 of 24)

- [FusionAD: Multi-modality Fusion for Prediction and Planning Tasks of Autonomous Driving](https://mlsanity.com/paper/2308.01006/) (2023)
- [A Survey of World Models for Autonomous Driving](https://mlsanity.com/paper/2501.11260/) (2025)
- [Cam4DOcc: Benchmark for Camera-Only 4D Occupancy Forecasting in Autonomous Driving Applications](https://mlsanity.com/paper/2311.17663/) (2023)
- [SpaceDrive: Infusing Spatial Awareness into VLM-based Autonomous Driving](https://mlsanity.com/paper/2512.10719/) (2025)
- [PointBeV: A Sparse Approach to BeV Predictions](https://mlsanity.com/paper/2312.00703/) (2023)
- [Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions](https://mlsanity.com/paper/2503.03262/) (2025)
- [MFTraj: Map-Free, Behavior-Driven Trajectory Prediction for Autonomous Driving](https://mlsanity.com/paper/2405.01266/) (2024)
- [Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond](https://mlsanity.com/paper/2405.14674/) (2024)
- [OccProphet: Pushing Efficiency Frontier of Camera-Only 4D Occupancy Forecasting with Observer-Forecaster-Refiner Framework](https://mlsanity.com/paper/2502.15180/) (2025)
- [AGO: Adaptive Grounding for Open World 3D Occupancy Prediction](https://mlsanity.com/paper/2504.10117/) (2025)
- [Joint Perception and Prediction for Autonomous Driving: A Survey](https://mlsanity.com/paper/2412.14088/) (2024)
- [ForecastOcc: Vision-based Semantic Occupancy Forecasting](https://mlsanity.com/paper/2602.08006/) (2026)
- [Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting](https://mlsanity.com/paper/2411.14169/) (2024)
- [FipTR: A Simple yet Effective Transformer Framework for Future Instance Prediction in Autonomous Driving](https://mlsanity.com/paper/2404.12867/) (2024)
- [RS-DFM: A Remote Sensing Distributed Foundation Model for Diverse Downstream Tasks](https://mlsanity.com/paper/2406.07032/) (2024)
- [Vision-Centric 4D Occupancy Forecasting and Planning via Implicit Residual World Models](https://mlsanity.com/paper/2510.16729/) (2025)
- [TAFormer: A Unified Target-Aware Transformer for Video and Motion Joint Prediction in Aerial Scenes](https://mlsanity.com/paper/2403.18238/) (2024)
- [Fast and Efficient Transformer-based Method for Bird's Eye View Instance Prediction](https://mlsanity.com/paper/2411.06851/) (2024)
- [UDA4Inst: Unsupervised Domain Adaptation for Instance Segmentation](https://mlsanity.com/paper/2405.09682/) (2024)
- [To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Software](https://mlsanity.com/paper/2508.20892/) (2025)
- [BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving](https://mlsanity.com/paper/2604.02930/) (2026)
- [BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentation](https://mlsanity.com/paper/2503.03280/) (2025)
- [TGRIP: A Text-Guided Approach to Vehicle Instance Prediction in Autonomous Driving](https://mlsanity.com/paper/2607.04812/) (2026)
- [InterOCF: Spatio-Temporal 2D-3D Interaction for Camera-Only 4D Occupancy Forecasting](https://mlsanity.com/paper/2607.24431/) (2026)

## Abstract (arXiv)

Accurately perceiving instances and predicting their future motion are key tasks for autonomous vehicles, enabling them to navigate safely in complex urban traffic. While bird's-eye view (BEV) representations are commonplace in perception for autonomous driving, their potential in a motion prediction setting is less explored. Existing approaches for BEV instance prediction from surround cameras rely on a multi-task auto-regressive setup coupled with complex post-processing to predict future instances in a spatio-temporally consistent manner. In this paper, we depart from this paradigm and propose an efficient novel end-to-end framework named POWERBEV, which differs in several design choices aimed at reducing the inherent redundancy in previous methods. First, rather than predicting the future in an auto-regressive fashion, POWERBEV uses a parallel, multi-scale module built from lightweight 2D convolutional networks. Second, we show that segmentation and centripetal backward flow are sufficient for prediction, simplifying previous multi-task objectives by eliminating redundant output modalities. Building on this output representation, we propose a simple, flow warping-based post-processing approach which produces more stable instance associations across time. Through this lightweight yet powerful design, POWERBEV outperforms state-of-the-art baselines on the NuScenes Dataset and poses an alternative paradigm for BEV instance prediction. We made our code publicly available at: https://github.com/EdwardLeeLPZ/PowerBEV.