用新方法融合多焦点图像，解决高分辨率成像中景深不足问题。
Addressing the Depth-of-Field Constraint: A New Paradigm for High Resolution Multi-Focus Image Fusion
- 基于蒸馏变分自编码器实现高效高保真图像重建。
- 可同时处理七张图像，融合效果无缝无伪影。
- 构建4K级合成数据集，提升真实场景适配能力，适合视觉科研与工业应用。
多焦点图像融合（MFIF）旨在克服光学镜头景深限制，使不同距离物体均清晰可见。尽管传统与深度学习方法有所进展，仍面临训练数据有限、合成数据与真实场景存在域差距、信息缺失区域难以处理等挑战。本文提出VAEEDOF，一种新型MFIF方法，采用蒸馏变分自编码器实现高保真、高效率的图像重建。其融合模块可同时处理最多七张图像，支持跨多个对焦点的鲁棒融合。为缓解数据稀缺问题，引入MattingMFIF，一个全新的4K级合成数据集，通过真实照片模拟出逼真的景深效果。实验表明，该方法达到当前最优性能，生成无缝且无伪影的融合图像，有效弥合了合成数据与真实世界之间的差距，显著推进了复杂多焦点融合难题的解决。代码与模型权重已公开。
原文摘要 · Abstract (English)
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:
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。