Tada-DIP通过自适应输入与去噪正则化，实现高质量3D图像单次重建。
Tada-DIP: Input-adaptive Deep Image Prior for One-shot 3D Image Reconstruction
- 根据输入图像自适应调整网络，提升3D重建精度
- 在稀疏视角CT重建中优于无训练基线方法
- 无需大量标注数据，适合低样本3D成像任务
深度图像先验（DIP）作为一种新兴的基于神经网络的单次图像重建方法，展现出巨大潜力。然而，其在三维图像重建中的应用仍受限。本文提出Tada-DIP，一种高效且完全基于3D的DIP方法，用于解决3D逆问题。通过结合输入自适应与去噪正则化，Tada-DIP在避免过拟合的同时，生成高质量的3D重建结果。在稀疏视角X射线计算机断层扫描重建实验中验证了该方法的有效性，结果显示，Tada-DIP的重建质量显著优于无训练基线方法，并达到与使用大规模全采样体积数据集训练的监督网络相当的性能。
原文摘要 · Abstract (English)
Deep Image Prior (DIP) has recently emerged as a promising one-shot neural-network based image reconstruction method. However, DIP has seen limited application to 3D image reconstruction problems. In this work, we introduce Tada-DIP, a highly effective and fully 3D DIP method for solving 3D inverse problems. By combining input-adaptation and denoising regularization, Tada-DIP produces high-quality 3D reconstructions while avoiding the overfitting phenomenon that is common in DIP. Experiments on sparse-view X-ray computed tomography reconstruction validate the effectiveness of the proposed method, demonstrating that Tada-DIP produces much better reconstructions than training-data-free baselines and achieves reconstruction performance on par with a supervised network trained using a large dataset with fully-sampled volumes.
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。