What question did this study set out to answer?

This research aims to enhance the generation of all-in-focus images from light field data without relying on depth estimation.

May 30, 2026

FDSNet: Frequency-Decoupled Stack Fusion Network for Light Field All-in-Focus Image Generation

Key Points

This research aims to enhance the generation of all-in-focus images from light field data without relying on depth estimation.
Proposed Frequency-Decoupled Stack Fusion Network (FDSNet) for image generation.
Utilized a spatial-frequency joint feature extraction module for multi-scale detail capture.
Implemented a dual-stage cross-attention fusion module to improve edge fidelity and reduce error accumulation.
FDSNet shows significant improvement in visual quality and quantitative metrics compared to existing methods.
Validates robustness in low-light and noisy conditions, showcasing enhanced clarity and detail preservation.
Outperformed state-of-the-art methods in fusion capability, providing better noise resistance and generalization.

Abstract

All-in-focus(AIF) images, which contain comprehensive scene information with global sharpness, play a crucial role in high-precision light field (LF) measurement and computational imaging. However, generating AIF images from LF data typically requires accurate depth priors, which are often unavailable or unreliable in practice. To overcome this limitation, directly fusing a series of LF refocused images provides an effective alternative that eliminates the dependency on explicit depth estimation. Nevertheless, existing multi-focus image fusion(MFIF) methods are primarily designed for fusing image pairs with complementary focus, performing poorly when applied to stacks due to the error accumulation that occurs during iterative fusion. To this end, we propose a Frequency-Decoupled Stack Fusion Network (FDSNet) for high-precision depth-free LF AIF image generation. FDSNet incorporates a spatial-frequency joint feature extraction module that captures multi-scale spatial details while decoupling high- and low- frequency components to model textures and contextual information separately, thereby alleviating edge blurring caused by subtle focal variations and weak textures in transition regions. Moreover, a dual-stage cross-attention fusion module, following a coarse-to-fine strategy, suppresses artifacts, enhances edge fidelity, and enables simultaneous fusion of arbitrary numbers of refocused images, thereby avoiding error accumulation and computational redundancy. Extensive experiments on both synthetic and real LF datasets demonstrate that FDSNet achieves superior visual quality and quantitative performance. Additional experiments further demonstrate that FDSNet performs robustly under varying low-light and noisy conditions. These results validate that FDSNet delivers excellent fusion capability in terms of image clarity, detail preservation, noise resistance, and generalization, outperforming existing state-of-the-art methods.

AI에게 질문

Bookmark