EvLIR: Learning Illumination Residuals from Ordered Events for Low-Light Image Enhancement

2026-06-28

AI Summary

This work addresses the challenges of low-light image enhancement—such as structural degradation, noise saturation, and weak local contrast—by proposing a temporal residual enhancement framework that leverages the high temporal resolution of event cameras. It introduces a lightweight Temporal Event Residual Module (TERM) that explicitly models temporal evolution within an event window, enabling spatially adaptive illumination correction and reliability-aware image-event fusion. Short-term event dynamics are encoded via ConvGRU, integrated with a Retinex-based illumination estimation, and refined through a bounded correction mechanism. Evaluated on four indoor and outdoor benchmarks (SDE and SDSD), the method achieves state-of-the-art performance in 11 out of 12 metrics, yielding an average PSNR of 25.63 dB (PSNR* 28.30 dB) and an SSIM of 0.827.

Abstract

Low-light image enhancement is severely ill-posed when the input frame contains missing structure, saturated noise, and weak local contrast. Event cameras provide asynchronous brightness-change observations with high temporal resolution, but prior works often treat voxel channels as an unordered or static feature stack before fusion, rather than explicitly modeling their within-window temporal evolution, weakening the temporal evidence that makes events useful. We propose EvLIR, a temporal-residual enhancement framework that learns illumination residuals from ordered events for low-light image enhancement. Given a low-light frame and its aligned event voxel, EvLIR preserves the ordered temporal bins of the event stream and introduces a Temporal Event Residual Module (TERM) to encode short-window event dynamics with a lightweight ConvGRU. The resulting temporal state is converted into a bounded illumination correction, which provides spatially adaptive photometric guidance for Retinex-style illumination estimation and subsequent reliability-aware image-event restoration. On SDE and SDSD indoor/outdoor benchmarks, EvLIR achieves the best result on eleven of twelve dataset-metric pairs, with average scores of 25.63~dB PSNR, 28.30~dB PSNR*, and 0.827 SSIM across the four benchmarks.

Problem

• low-light image enhancement
• event cameras
• temporal evolution
• illumination residuals
• image restoration

Innovation

• event camera
• temporal residual learning
• low-light image enhancement
• illumination estimation
• ConvGRU