Adapting Depth Anything to Adverse Imaging Conditions with Events

2026-01-05

arXiv.org

AI Summary

This work addresses the significant performance degradation of existing depth estimation models, such as Depth Anything, under adverse imaging conditions including extreme illumination and motion blur. To tackle this challenge, we propose ADAE, a plug-and-play framework that seamlessly integrates event camera data into foundation depth models without requiring retraining, thereby preserving their open-world generalization capability. ADAE jointly models illumination degradation and motion blur through entropy-aware spatial feature fusion and event-guided temporal motion correction, establishing a unified spatiotemporal fusion architecture. Experimental results demonstrate that ADAE substantially enhances the accuracy and robustness of Depth Anything across diverse degradation scenarios.

Technology Category

• Computer Vision: Other Foundations of Computer Vision
• Machine Learning: Deep Neural Architectures and Foundation Models
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Robust depth estimation under dynamic and adverse lighting conditions is essential for robotic systems. Currently, depth foundation models, such as Depth Anything, achieve great success in ideal scenes but remain challenging under adverse imaging conditions such as extreme illumination and motion blur. These degradations corrupt the visual signals of frame cameras, weakening the discriminative features of frame-based depths across the spatial and temporal dimensions. Typically, existing approaches incorporate event cameras to leverage their high dynamic range and temporal resolution, aiming to compensate for corrupted frame features. However, such specialized fusion models are predominantly trained from scratch on domain-specific datasets, thereby failing to inherit the open-world knowledge and robust generalization inherent to foundation models. In this work, we propose ADAE, an event-guided spatiotemporal fusion framework for Depth Anything in degraded scenes. Our design is guided by two key insights: 1) Entropy-Aware Spatial Fusion. We adaptively merge frame-based and event-based features using an information entropy strategy to indicate illumination-induced degradation. 2) Motion-Guided Temporal Correction. We resort to the event-based motion cue to recalibrate ambiguous features in blurred regions. Under our unified framework, the two components are complementary to each other and jointly enhance Depth Anything under adverse imaging conditions. Extensive experiments have been performed to verify the superiority of the proposed method. Our code will be released upon acceptance.

Problem

• depth estimation
• adverse imaging conditions
• event cameras
• motion blur
• extreme illumination

Innovation

• event camera
• depth estimation
• adverse imaging conditions
• spatiotemporal fusion
• foundation model adaptation