Cover Image

Revisiting Birds Eye View Perception Models with Frozen Foundation Models: DINOv2 and Metric3Dv2

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hayes, Seamie, Sistu, Ganesh, Eising, Ciarán
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Easy3D-Labels: Supervising Semantic Occupancy Estimation with 3D Pseudo-Labels for Automotive Perception
by: Hayes, Seamie, et al.
Published: (2025)

Velocity Driven Vision: Asynchronous Sensor Fusion Birds Eye View Models for Autonomous Vehicles
by: Hayes, Seamie, et al.
Published: (2024)

Fisheye Camera and Ultrasonic Sensor Fusion For Near-Field Obstacle Perception in Bird's-Eye-View
by: Das, Arindam, et al.
Published: (2024)

Optimizing Visual Question Answering Models for Driving: Bridging the Gap Between Human and Machine Attention Patterns
by: Rekanar, Kaavya, et al.
Published: (2024)

SuperQuadricOcc: Real-Time Self-Supervised Semantic Occupancy Estimation with Superquadric Volume Rendering
by: Hayes, Seamie, et al.
Published: (2025)

Reflective Teacher: Semi-Supervised Multimodal 3D Object Detection in Bird's-Eye-View via Uncertainty Measure
by: Hazra, Saheli, et al.
Published: (2024)

Minimizing Occlusion Effect on Multi-View Camera Perception in BEV with Multi-Sensor Fusion
by: Kumar, Sanjay, et al.
Published: (2025)

Evaluating Small Vision-Language Models on Distance-Dependent Traffic Perception
by: Theodoridis, Nikos, et al.
Published: (2025)

MapsTP: HD Map Images Based Multimodal Trajectory Prediction for Automated Vehicles
by: Sharma, Sushil, et al.
Published: (2024)

Optimizing Ego Vehicle Trajectory Prediction: The Graph Enhancement Approach
by: Sharma, Sushil, et al.
Published: (2023)

Robust Bird's Eye View Segmentation by Adapting DINOv2
by: Barın, Merve Rabia, et al.
Published: (2024)

Probing Visual Concepts in Lightweight Vision-Language Models for Automated Driving
by: Theodoridis, Nikos, et al.
Published: (2026)

Occluded nuScenes: A Multi-Sensor Dataset for Evaluating Perception Robustness in Automated Driving
by: Kumar, Sanjay, et al.
Published: (2025)

Evaluating the Impact of Weather-Induced Sensor Occlusion on BEVFusion for 3D Object Detection
by: Kumar, Sanjay, et al.
Published: (2025)

Descriptor: Distance-Annotated Traffic Perception Question Answering (DTPQA)
by: Theodoridis, Nikos, et al.
Published: (2025)

FisheyeGaussianLift: BEV Feature Lifting for Surround-View Fisheye Camera Perception
by: Sonarghare, Shubham, et al.
Published: (2025)

Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation
by: Hu, Mu, et al.
Published: (2024)

Deformable Convolution Based Road Scene Semantic Segmentation of Fisheye Images in Autonomous Driving
by: Manzoor, Anam, et al.
Published: (2024)

BEVMOSNet: Multimodal Fusion for BEV Moving Object Segmentation
by: Cong, Hiep Truong, et al.
Published: (2025)

NeurAll: Towards a Unified Visual Perception Model for Automated Driving
by: Sistu, Ganesh, et al.
Published: (2019)

DINO-MVR: Multi-View Readout of Frozen DINOv3 for Annotation-Efficient Medical Segmentation
by: Jiang, Wei, et al.
Published: (2026)

BEVCon: Advancing Bird's Eye View Perception with Contrastive Learning
by: Leng, Ziyang, et al.
Published: (2025)

Unveiling the Black Box: Independent Functional Module Evaluation for Bird's-Eye-View Perception Model
by: Zhang, Ludan, et al.
Published: (2024)

FisheyeDetNet: 360° Surround view Fisheye Camera based Object Detection System for Autonomous Driving
by: Sistu, Ganesh, et al.
Published: (2024)

Vision-Driven 2D Supervised Fine-Tuning Framework for Bird's Eye View Perception
by: He, Lei, et al.
Published: (2024)

Learning to Adapt Foundation Model DINOv2 for Capsule Endoscopy Diagnosis
by: Zhang, Bowen, et al.
Published: (2024)

DA-BEV: Unsupervised Domain Adaptation for Bird's Eye View Perception
by: Jiang, Kai, et al.
Published: (2024)

Fast-BEV: A Fast and Strong Bird's-Eye View Perception Baseline
by: Li, Yangguang, et al.
Published: (2023)

Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving
by: Xie, Shaoyuan, et al.
Published: (2024)

RopeBEV: A Multi-Camera Roadside Perception Network in Bird's-Eye-View
by: Jia, Jinrang, et al.
Published: (2024)

OnlineBEV: Recurrent Temporal Fusion in Bird's Eye View Representations for Multi-Camera 3D Perception
by: Koh, Junho, et al.
Published: (2025)

Lifting Multi-View Detection and Tracking to the Bird's Eye View
by: Teepe, Torben, et al.
Published: (2024)

DINOv3 as a Frozen Encoder for CRPS-Oriented Probabilistic Rainfall Nowcasting
by: Filho, Luciano Araujo Dourado, et al.
Published: (2025)

FrozenSeg: Harmonizing Frozen Foundation Models for Open-Vocabulary Segmentation
by: Chen, Xi, et al.
Published: (2024)

From SAM to DINOv2: Towards Distilling Foundation Models to Lightweight Baselines for Generalized Polyp Segmentation
by: Agnihotri, Shivanshu, et al.
Published: (2025)

DINOv3 Beats Specialized Detectors: A Simple Foundation Model Baseline for Image Forensics
by: Yu, Jieming, et al.
Published: (2026)

Progressive Bird's Eye View Perception for Safety-Critical Autonomous Driving: A Comprehensive Survey
by: Gong, Yan, et al.
Published: (2025)

Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
by: Fu, Shenghao, et al.
Published: (2024)

Street-View Image Generation from a Bird's-Eye View Layout
by: Swerdlow, Alexander, et al.
Published: (2023)

Holistic Autonomous Driving Understanding by Bird's-Eye-View Injected Multi-Modal Large Models
by: Ding, Xinpeng, et al.
Published: (2024)