Bidirectional Image-Event Guided Fusion Framework for Low-Light Image Enhancement

TL;DR

This paper introduces BiLIE, a novel bidirectional fusion framework for low-light image enhancement using image and event data, effectively reducing flickering artifacts and structural discontinuities under extreme lighting conditions.

Contribution

The paper proposes a new fusion framework with adaptive filtering and attention mechanisms, and constructs a high-quality dataset for low-light image-event enhancement.

Findings

Outperforms existing methods on RELIE and LIE datasets.

Achieves 0.81dB higher PSNR on RELIE.

Shows superior edge restoration, color fidelity, and noise suppression.

Abstract

Under extreme low-light conditions, frame-based cameras suffer from severe detail loss due to limited dynamic range. Recent studies have introduced event cameras for event-guided low-light image enhancement. However, existing approaches often overlook the flickering artifacts and structural discontinuities caused by dynamic illumination changes and event sparsity. To address these challenges, we propose BiLIE, a Bidirectional image-event guided fusion framework for Low-Light Image Enhancement, which achieves mutual guidance and complementary enhancement between the two modalities. First, to highlight edge details, we develop a Dynamic Adaptive Filtering Enhancement (DAFE) module that performs adaptive high-pass filtering on event representations to suppress flickering artifacts and preserve high-frequency information under varying illumination. Subsequently, we design a Bidirectional Guided Awareness Fusion (BGAF) mechanism, which achieves breakpoint-aware restoration from images to events and structure-aware enhancement from events to images through a two-stage attention mechanism, establishing cross-modal consistency, thereby producing a clear, smooth, and structurally intact fused representation. Moreover, recognizing that existing datasets exhibit insufficient ground-truth fidelity and color accuracy, we construct a high-quality low-light image-event dataset (RELIE) via a reliable ground truth refinement scheme. Extensive experiments demonstrate that our method outperforms existing approaches on both the RELIE and LIE datasets. Notably, on RELIE, BiLIE exceeds the state-of-the-art by 0.81dB in PSNR and shows significant advantages in edge restoration, color fidelity, and noise suppression.