Tada-DIP: Input-adaptive Deep Image Prior for One-shot 3D Image Reconstruction
This addresses 3D inverse problems like sparse-view CT reconstruction for medical imaging, but it is incremental as it builds on the existing Deep Image Prior framework.
The paper tackled 3D image reconstruction from sparse data by introducing Tada-DIP, a method that avoids overfitting and produces high-quality 3D reconstructions, achieving performance comparable to supervised networks trained on large datasets.
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.