# Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer

arXiv: https://arxiv.org/abs/2206.04584 · HTML: https://mlsanity.com/paper/2206.04584/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 11 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 10 of 10)

- [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)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (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)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras](https://mlsanity.com/paper/2104.10490/) (2021)
- [Orthographic Feature Transform for Monocular 3D Object Detection](https://mlsanity.com/paper/1811.08188/) (2018)
- [Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks](https://mlsanity.com/paper/2003.13402/) (2020)
- [Cross-view Semantic Segmentation for Sensing Surroundings](https://mlsanity.com/paper/1906.03560/) (2019)

## Built on by (most cited first, 30 of 80)

- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Driving](https://mlsanity.com/paper/2411.15139/) (2024)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024)
- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [Vision-Centric BEV Perception: A Survey](https://mlsanity.com/paper/2208.02797/) (2022)
- [Symphonize 3D Semantic Scene Completion with Contextual Instance Queries](https://mlsanity.com/paper/2306.15670/) (2023)
- [CRN: Camera Radar Net for Accurate, Robust, Efficient 3D Perception](https://mlsanity.com/paper/2304.00670/) (2023)
- [Online Map Vectorization for Autonomous Driving: A Rasterization Perspective](https://mlsanity.com/paper/2306.10502/) (2023)
- [Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction](https://mlsanity.com/paper/2303.08815/) (2023)
- [HIMap: HybrId Representation Learning for End-to-end Vectorized HD Map Construction](https://mlsanity.com/paper/2403.08639/) (2024)
- [Leveraging Enhanced Queries of Point Sets for Vectorized Map Construction](https://mlsanity.com/paper/2402.17430/) (2024)
- [Localization Is All You Evaluate: Data Leakage in Online Mapping Datasets and How to Fix It](https://mlsanity.com/paper/2312.06420/) (2023)
- [Online Vectorized HD Map Construction using Geometry](https://mlsanity.com/paper/2312.03341/) (2023)
- [InstaGraM: Instance-level Graph Modeling for Vectorized HD Map Learning](https://mlsanity.com/paper/2301.04470/) (2023)
- [Camera-based 3D Semantic Scene Completion with Sparse Guidance Network](https://mlsanity.com/paper/2312.05752/) (2023)
- [A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective](https://mlsanity.com/paper/2405.05173/) (2024)
- [Enhancing Vectorized Map Perception with Historical Rasterized Maps](https://mlsanity.com/paper/2409.00620/) (2024)
- [Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction](https://mlsanity.com/paper/2212.02181/) (2022)
- [Is Your HD Map Constructor Reliable under Sensor Corruptions?](https://mlsanity.com/paper/2406.12214/) (2024)
- [MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation](https://mlsanity.com/paper/2407.11682/) (2024)
- [Grid-Centric Traffic Scenario Perception for Autonomous Driving: A Comprehensive Review](https://mlsanity.com/paper/2303.01212/) (2023)
- [Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation](https://mlsanity.com/paper/2207.01878/) (2022)
- [Enhancing 3D Lane Detection and Topology Reasoning with 2D Lane Priors](https://mlsanity.com/paper/2406.03105/) (2024)
- [BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks](https://mlsanity.com/paper/2212.01231/) (2022)
- [MapLocNet: Coarse-to-Fine Feature Registration for Visual Re-Localization in Navigation Maps](https://mlsanity.com/paper/2407.08561/) (2024)
- [Neural Groundplans: Persistent Neural Scene Representations from a Single Image](https://mlsanity.com/paper/2207.11232/) (2022)
- [Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Driving](https://mlsanity.com/paper/2305.04205/) (2023)
- [SafeMap: Robust HD Map Construction from Incomplete Observations](https://mlsanity.com/paper/2507.00861/) (2025)
- [Improving Bird's Eye View Semantic Segmentation by Task Decomposition](https://mlsanity.com/paper/2404.01925/) (2024)

## Abstract (arXiv)

Learning Bird's Eye View (BEV) representation from surrounding-view cameras is of great importance for autonomous driving. In this work, we propose a Geometry-guided Kernel Transformer (GKT), a novel 2D-to-BEV representation learning mechanism. GKT leverages the geometric priors to guide the transformer to focus on discriminative regions and unfolds kernel features to generate BEV representation. For fast inference, we further introduce a look-up table (LUT) indexing method to get rid of the camera's calibrated parameters at runtime. GKT can run at 72.3 FPS on 3090 GPU / 45.6 FPS on 2080ti GPU and is robust to the camera deviation and the predefined BEV height. And GKT achieves the state-of-the-art real-time segmentation results, i.e., 38.0 mIoU (100m×100m perception range at a 0.5m resolution) on the nuScenes val set. Given the efficiency, effectiveness, and robustness, GKT has great practical values in autopilot scenarios, especially for real-time running systems. Code and models will be available at urlhttps://github.com/hustvl/GKT.