Depth AnyEvent: A Cross-Modal Distillation Paradigm for Event-Based Monocular Depth Estimation

2025/09/18 by Bartolomei, Luca, Mannocci, Enrico, Tosi, Fabio +2
#Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2509.15224

Abstract

Event cameras capture sparse, high-temporal-resolution visual information, making them particularly suitable for challenging environments with high-speed motion and strongly varying lighting conditions. However, the lack of large datasets with dense ground-truth depth annotations hinders learning-based monocular depth estimation from event data. To address this limitation, we propose a cross-modal distillation paradigm to generate dense proxy labels leveraging a Vision Foundation Model (VFM). Our strategy requires an event stream spatially aligned with RGB frames, a simple setup even available off-the-shelf, and exploits the robustness of large-scale VFMs. Additionally, we propose to adapt VFMs, either a vanilla one like Depth Anything v2 (DAv2), or deriving from it a novel recurrent architecture to infer depth from monocular event cameras. We evaluate our approach with synthetic and real-world datasets, demonstrating that i) our cross-modal paradigm achieves competitive performance compared to fully supervised methods without requiring expensive depth annotations, and ii) our VFM-based models achieve state-of-the-art performance.

Citations

• Event-based Stereo Depth Estimation: A Survey
• LiDAR-Event Stereo Fusion with Hallucinations
• Depth Anything V2
• Learning Temporally Consistent Video Depth from Video Diffusion Priors
• Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
• Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image
• Towards Zero-Shot Scale-Aware Monocular Depth Estimation
• DINOv2: Learning Robust Visual Features without Supervision
• DDP: Diffusion Model for Dense Visual Prediction
• DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation
• Monocular Depth Estimation using Diffusion Models
• EventPoint: Self-Supervised Interest Point Detection and Description for Event-based Camera
• Vision Transformers for Dense Prediction
• DSEC: A Stereo Event Camera Dataset for Driving Scenarios
• Learning Monocular Dense Depth from Events
• DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data
• Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer
• Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-Shot Cross-Dataset Transfer
• CED: Color Event Camera Dataset
• Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion
• MegaDepth: Learning Single-View Depth Prediction from Internet Photos
• CARLA: An Open Urban Driving Simulator
• Unsupervised Learning of Depth and Ego-Motion from Video
• Unsupervised Monocular Depth Estimation with Left-Right Consistency
• Deeper Depth Prediction with Fully Convolutional Residual Networks
• Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network

Related

• Self-supervised Event-based Monocular Depth Estimation using Cross-modal Consistency
• Learning Monocular Dense Depth from Events
• Learning Monocular Depth from Events via Egomotion Compensation
• Dense Depth from Event Focal Stack
• Event-based Monocular Dense Depth Estimation with Recurrent Transformers