# Robust Bird's Eye View Segmentation by Adapting DINOv2

arXiv: https://arxiv.org/abs/2409.10228 · HTML: https://mlsanity.com/paper/2409.10228/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 32 references that are in the map.
- First posted on arXiv 16 Sep 2024.

## Builds on (most cited first, 29 of 29)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [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)
- [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)
- [Argoverse: 3D Tracking and Forecasting with Rich Maps](https://mlsanity.com/paper/1911.02620/) (2019)
- [BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detection](https://mlsanity.com/paper/2206.10092/) (2022)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Cross-view Transformers for real-time Map-view Semantic Segmentation](https://mlsanity.com/paper/2205.02833/) (2022)
- [End-to-End Urban Driving by Imitating a Reinforcement Learning Coach](https://mlsanity.com/paper/2108.08265/) (2021)
- [Probing the 3D Awareness of Visual Foundation Models](https://mlsanity.com/paper/2404.08636/) (2024)
- [Learning from All Vehicles](https://mlsanity.com/paper/2203.11934/) (2022)
- [Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?](https://mlsanity.com/paper/2206.07959/) (2022)
- [KING: Generating Safety-Critical Driving Scenarios for Robust Imitation via Kinematics Gradients](https://mlsanity.com/paper/2204.13683/) (2022)
- [CNOS: A Strong Baseline for CAD-based Novel Object Segmentation](https://mlsanity.com/paper/2307.11067/) (2023)
- [Self-supervised Object-Centric Learning for Videos](https://mlsanity.com/paper/2310.06907/) (2023)
- [RoboBEV: Towards Robust Bird's Eye View Perception under Corruptions](https://mlsanity.com/paper/2304.06719/) (2023)
- [MeLo: Low-rank Adaptation is Better than Fine-tuning for Medical Image Diagnosis](https://mlsanity.com/paper/2311.08236/) (2023)
- [LaRa: Latents and Rays for Multi-Camera Bird's-Eye-View Semantic Segmentation](https://mlsanity.com/paper/2206.13294/) (2022)
- [BEVCar: Camera-Radar Fusion for BEV Map and Object Segmentation](https://mlsanity.com/paper/2403.11761/) (2024)
- [PointBeV: A Sparse Approach to BeV Predictions](https://mlsanity.com/paper/2312.00703/) (2023)
- [Towards Motion Forecasting with Real-World Perception Inputs: Are End-to-End Approaches Competitive?](https://mlsanity.com/paper/2306.09281/) (2023)
- [OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks](https://mlsanity.com/paper/2404.14027/) (2024)
- [Can Visual Foundation Models Achieve Long-term Point Tracking?](https://mlsanity.com/paper/2408.13575/) (2024)
- [CoViS-Net: A Cooperative Visual Spatial Foundation Model for Multi-Robot Applications](https://mlsanity.com/paper/2405.01107/) (2024)

## Built on by (most cited first, 6 of 6)

- [Driving on Registers](https://mlsanity.com/paper/2601.05083/) (2026)
- [Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking](https://mlsanity.com/paper/2510.10287/) (2025)
- [Order Matters: On Parameter-Efficient Image-to-Video Probing for Recognizing Nearly Symmetric Actions](https://mlsanity.com/paper/2503.24298/) (2025)
- [FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed](https://mlsanity.com/paper/2507.03779/) (2025)
- [FishBEV: Distortion-Resilient Bird's Eye View Segmentation with Surround-View Fisheye Cameras](https://mlsanity.com/paper/2509.13681/) (2025)
- [MapFM: Foundation Model-Driven HD Mapping with Multi-Task Contextual Learning](https://mlsanity.com/paper/2506.15313/) (2025)

## Abstract (arXiv)

Extracting a Bird's Eye View (BEV) representation from multiple camera images offers a cost-effective, scalable alternative to LIDAR-based solutions in autonomous driving. However, the performance of the existing BEV methods drops significantly under various corruptions such as brightness and weather changes or camera failures. To improve the robustness of BEV perception, we propose to adapt a large vision foundational model, DINOv2, to BEV estimation using Low Rank Adaptation (LoRA). Our approach builds on the strong representation space of DINOv2 by adapting it to the BEV task in a state-of-the-art framework, SimpleBEV. Our experiments show increased robustness of BEV perception under various corruptions, with increasing gains from scaling up the model and the input resolution. We also showcase the effectiveness of the adapted representations in terms of fewer learnable parameters and faster convergence during training.