# MapDistill: Boosting Efficient Camera-based HD Map Construction via Camera-LiDAR Fusion Model Distillation

arXiv: https://arxiv.org/abs/2407.11682 · HTML: https://mlsanity.com/paper/2407.11682/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 45 of its 54 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 45)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [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)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [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)
- [BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation](https://mlsanity.com/paper/2205.13542/) (2022)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions](https://mlsanity.com/paper/2211.05778/) (2022)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2208.14437/) (2022)
- [BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision](https://mlsanity.com/paper/2211.10439/) (2022)
- [HDMapNet: An Online HD Map Construction and Evaluation Framework](https://mlsanity.com/paper/2107.06307/) (2021)
- [DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification](https://mlsanity.com/paper/2203.12081/) (2022)
- [VectorMapNet: End-to-end Vectorized HD Map Learning](https://mlsanity.com/paper/2206.08920/) (2022)
- [Unifying Voxel-based Representation with Transformer for 3D Object Detection](https://mlsanity.com/paper/2206.00630/) (2022)
- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving](https://mlsanity.com/paper/2205.09743/) (2022)
- [2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds](https://mlsanity.com/paper/2207.04397/) (2022)
- [PivotNet: Vectorized Pivot Learning for End-to-end HD Map Construction](https://mlsanity.com/paper/2308.16477/) (2023)
- [End-to-End Vectorized HD-map Construction with Piecewise Bezier Curve](https://mlsanity.com/paper/2306.09700/) (2023)
- [Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer](https://mlsanity.com/paper/2206.04584/) (2022)
- [Neural Map Prior for Autonomous Driving](https://mlsanity.com/paper/2304.08481/) (2023)
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022)
- [FISHING Net: Future Inference of Semantic Heatmaps In Grids](https://mlsanity.com/paper/2006.09917/) (2020)
- [Online Map Vectorization for Autonomous Driving: A Rasterization Perspective](https://mlsanity.com/paper/2306.10502/) (2023)

## Built on by (most cited first, 26 of 26)

- [JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation](https://mlsanity.com/paper/2509.22548/) (2025)
- [GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving](https://mlsanity.com/paper/2511.18729/) (2025)
- [MapFusion: A Novel BEV Feature Fusion Network for Multi-modal Map Construction](https://mlsanity.com/paper/2502.04377/) (2025)
- [MSC-Bench: Benchmarking and Analyzing Multi-Sensor Corruption for Driving Perception](https://mlsanity.com/paper/2501.01037/) (2025)
- [SafeMap: Robust HD Map Construction from Incomplete Observations](https://mlsanity.com/paper/2507.00861/) (2025)
- [Rethinking Driving World Model as Synthetic Data Generator for Perception Tasks](https://mlsanity.com/paper/2510.19195/) (2025)
- [RENO: Real-Time Neural Compression for 3D LiDAR Point Clouds](https://mlsanity.com/paper/2503.12382/) (2025)
- [What Really Matters for Robust Multi-Sensor HD Map Construction?](https://mlsanity.com/paper/2507.01484/) (2025)
- [Stability Under Scrutiny: Benchmarking Representation Paradigms for Online HD Mapping](https://mlsanity.com/paper/2510.10660/) (2025)
- [Uni-PrevPredMap: Extending PrevPredMap to a Unified Framework of Prior-Informed Modeling for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2504.06647/) (2025)
- [SP2T: Sparse Proxy Attention for Dual-stream Point Transformer](https://mlsanity.com/paper/2412.11540/) (2024)
- [MapKD: Unlocking Prior Knowledge with Cross-Modal Distillation for Efficient Online HD Map Construction](https://mlsanity.com/paper/2508.15653/) (2025)
- [DSBench: A Comprehensive Benchmark for Evaluating External and In-Cabin Risks](https://mlsanity.com/paper/2511.14592/) (2025)
- [EagleVision: A Dual-Stage Framework with BEV-grounding-based Chain-of-Thought for Spatial Intelligence](https://mlsanity.com/paper/2512.15160/) (2025)
- [SatMap: Revisiting Satellite Maps as Prior for Online HD Map Construction](https://mlsanity.com/paper/2601.10512/) (2026)
- [BridgeTA: Bridging the Representation Gap in Knowledge Distillation via Teacher Assistant for Bird's Eye View Map Segmentation](https://mlsanity.com/paper/2508.09599/) (2025)
- [KD360-VoxelBEV: LiDAR and 360-degree Camera Cross Modality Knowledge Distillation for Bird's-Eye-View Segmentation](https://mlsanity.com/paper/2512.15311/) (2025)
- [AMap: Distilling Future Priors for Ahead-Aware Online HD Map Construction](https://mlsanity.com/paper/2512.19150/) (2025)
- [SEF-MAP: Subspace-Decomposed Expert Fusion for Robust Multimodal HD Map Prediction](https://mlsanity.com/paper/2602.21589/) (2026)
- [Online Navigation Refinement: Achieving Lane-Level Guidance by Associating Standard-Definition and Online Perception Maps](https://mlsanity.com/paper/2507.07487/) (2025)
- [Learning Global Representation from Queries for Vectorized HD Map Construction](https://mlsanity.com/paper/2510.06969/) (2025)
- [Learning Ego-Centric BEV Representations from a Perspective-Privileged View: Cross-View Supervision for Online HD Map Construction](https://mlsanity.com/paper/2605.12218/) (2026)
- [AerialFusionMapNet: Online HD Map Construction with Aerial-Onboard BEV Fusion](https://mlsanity.com/paper/2606.24784/) (2026)
- [Uncertainty-Aware Trajectory Prediction: A Unified Framework Harnessing Positional and Semantic Uncertainties](https://mlsanity.com/paper/2603.29362/) (2026)
- [LIE: LiDAR-only HD Map Construction with Intensity Enhancement via Online Knowledge Distillation](https://mlsanity.com/paper/2605.01478/) (2026)
- [HRDX: A Large-Scale Vector HD-Map Dataset](https://mlsanity.com/paper/2606.17080/) (2026)

## Abstract (arXiv)

Online high-definition (HD) map construction is an important and challenging task in autonomous driving. Recently, there has been a growing interest in cost-effective multi-view camera-based methods without relying on other sensors like LiDAR. However, these methods suffer from a lack of explicit depth information, necessitating the use of large models to achieve satisfactory performance. To address this, we employ the Knowledge Distillation (KD) idea for efficient HD map construction for the first time and introduce a novel KD-based approach called MapDistill to transfer knowledge from a high-performance camera-LiDAR fusion model to a lightweight camera-only model. Specifically, we adopt the teacher-student architecture, i.e., a camera-LiDAR fusion model as the teacher and a lightweight camera model as the student, and devise a dual BEV transform module to facilitate cross-modal knowledge distillation while maintaining cost-effective camera-only deployment. Additionally, we present a comprehensive distillation scheme encompassing cross-modal relation distillation, dual-level feature distillation, and map head distillation. This approach alleviates knowledge transfer challenges between modalities, enabling the student model to learn improved feature representations for HD map construction. Experimental results on the challenging nuScenes dataset demonstrate the effectiveness of MapDistill, surpassing existing competitors by over 7.7 mAP or 4.5X speedup.