Abstract:Light-field microscopy (LFM) enables single-shot capture of multi-angular information from biological samples, supporting real-time volumetric imaging. However, traditional physics-based algorithms often suffer from limited spatial resolution, severe artifacts, and high computational costs. Existing learning-based methods improve inference efficiency but still face limitations in reconstruction accuracy and generalization capability. To address these challenges, this paper proposes a high-fidelity Three-Step Conditional Diffusion (TCD) 3D reconstruction method for LFM. Although conventional diffusion models have achieved remarkable success in generative modeling, their slow sampling process and the inherent trade-off between quality and efficiency hinder their application in real-time 3D imaging. We redesign the diffusion process through a deterministic three-step sampling strategy coupled with a lightweight conditional U-Net, establishing a new paradigm for fast and accurate volumetric reconstruction. Furthermore, an Inter-Class Detection (ICD) module is incorporated to identify out-of-distribution or anomalous inputs during inference, thereby enhancing model stability and reliability. Extensive experiments and cross-dataset evaluations demonstrate that TCD significantly outperforms state-of-the-art methods in both reconstruction fidelity and generalization, providing an efficient and practical 3D reconstruction solution for light-field microscopy.
| Comments: | 10 pages, 6 figures. Accepted to CVPR 2026 Findings |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2605.24959 [cs.CV] |
| (or arXiv:2605.24959v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24959 arXiv-issued DOI via DataCite (pending registration) |
From: Qihong Zhao [view email]
[v1]
Sun, 24 May 2026 09:16:35 UTC (2,088 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。