High Dynamic Range Imaging Based on an Asymmetric Event-SVE Camera System

2026-02-28

AI Summary

This work addresses the challenge of high-quality HDR imaging under extreme illumination, where conventional cameras suffer from overexposure. The authors propose a hardware-algorithm co-designed asymmetric dual-modality system that, for the first time, integrates an off-axis event camera with a spatially varying exposure (SVE) micro-attenuation camera. They further introduce a two-stage cross-modal alignment and fusion network, which achieves joint optimization of optical and computational imaging through feature-guided coarse registration, multi-scale spatial-frequency domain fine alignment, and a learnable fusion loss. Experiments demonstrate that the proposed method significantly outperforms single-modality HDR approaches on both synthetic and real-world datasets, achieving state-of-the-art performance in highlight recovery, edge fidelity, and robustness.

Technology Category

• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Hardware-aware ML

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Security and Privacy: Data transparency and provenance
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

High dynamic range (HDR) imaging under extreme illumination remains challenging for conventional cameras due to overexposure. Event cameras provide microsecond temporal resolution and high dynamic range, while spatially varying exposure (SVE) sensors offer single-shot radiometric diversity.We present a hardware--algorithm co-designed HDR imaging system that tightly integrates an SVE micro-attenuation camera with an event sensor in an asymmetric dual-modality configuration. To handle non-coaxial geometry and heterogeneous optics, we develop a two-stage cross-modal alignment framework that combines feature-guided coarse homography estimation with a multi-scale refinement module based on spatial pooling and frequency-domain filtering. On top of aligned representations, we develop a cross-modal HDR reconstruction network with convolutional fusion, mutual-information regularization, and a learnable fusion loss that adaptively balances intensity cues and event-derived structural constraints. Comprehensive experiments on both synthetic benchmarks and real captures demonstrate that the proposed system consistently improves highlight recovery, edge fidelity, and robustness compared with frame-only or event-only HDR pipelines. The results indicate that jointly optimizing optical design, cross-modal alignment, and computational fusion provides an effective foundation for reliable HDR perception in highly dynamic and radiometrically challenging environments.

Problem

• High Dynamic Range Imaging
• Extreme Illumination
• Overexposure
• Event Camera
• Spatially Varying Exposure

Innovation

• event camera
• spatially varying exposure (SVE)
• cross-modal alignment
• HDR reconstruction
• hardware-algorithm co-design