Addressing the Depth-of-Field Constraint: A New Paradigm for High Resolution Multi-Focus Image Fusion

TL;DR

This paper introduces VAEEDOF, a novel variational autoencoder-based approach for high-resolution multi-focus image fusion, addressing data scarcity and domain gaps with a new synthetic dataset, achieving state-of-the-art results.

Contribution

It presents VAEEDOF, a new deep learning method for MFIF, and MattingMFIF, a synthetic dataset to improve training and domain adaptation.

Findings

Achieves state-of-the-art fusion quality.

Effectively handles diverse focus points.

Bridges synthetic and real-world data gaps.

Abstract

Multi-focus image fusion (MFIF) addresses the depth-of-field (DOF) limitations of optical lenses, where only objects within a specific range appear sharp. Although traditional and deep learning methods have advanced the field, challenges persist, including limited training data, domain gaps from synthetic datasets, and difficulties with regions lacking information. We propose VAEEDOF, a novel MFIF method that uses a distilled variational autoencoder for high-fidelity, efficient image reconstruction. Our fusion module processes up to seven images simultaneously, enabling robust fusion across diverse focus points. To address data scarcity, we introduce MattingMFIF, a new syntetic 4K dataset, simulating realistic DOF effects from real photographs. Our method achieves state-of-the-art results, generating seamless artifact-free fused images and bridging the gap between synthetic and real-world scenarios, offering a significant step forward in addressing complex MFIF challenges. The code, and weights are available here: