DFDNet: Dynamic Frequency-Guided De-Flare Network

TL;DR

This paper introduces DFDNet, a novel neural network that effectively removes large-scale flare artifacts in nighttime images by leveraging frequency domain guidance and contrastive learning to improve visual quality and detail preservation.

Contribution

The paper proposes a dynamic frequency-guided deflare network with a global frequency guidance module and a local detail guidance module, advancing flare removal techniques in nighttime photography.

Findings

Outperforms state-of-the-art flare removal methods

Effectively removes large-scale flare artifacts

Preserves fine image details during deflare process

Abstract

Strong light sources in nighttime photography frequently produce flares in images, significantly degrading visual quality and impacting the performance of downstream tasks. While some progress has been made, existing methods continue to struggle with removing large-scale flare artifacts and repairing structural damage in regions near the light source. We observe that these challenging flare artifacts exhibit more significant discrepancies from the reference images in the frequency domain compared to the spatial domain. Therefore, this paper presents a novel dynamic frequency-guided deflare network (DFDNet) that decouples content information from flare artifacts in the frequency domain, effectively removing large-scale flare artifacts. Specifically, DFDNet consists mainly of a global dynamic frequency-domain guidance (GDFG) module and a local detail guidance module (LDGM). The GDFG module guides the network to perceive the frequency characteristics of flare artifacts by dynamically optimizing global frequency domain features, effectively separating flare information from content information. Additionally, we design an LDGM via a contrastive learning strategy that aligns the local features of the light source with the reference image, reduces local detail damage from flare removal, and improves fine-grained image restoration. The experimental results demonstrate that the proposed method outperforms existing state-of-the-art methods in terms of performance. The code is available at \href{https://github.com/AXNing/DFDNet}{https://github.com/AXNing/DFDNet}.