SPLIT: Self-supervised Partitioning for Learned Inversion in Nonlinear Tomography

arXiv:2604.15651v1 Announce Type: new Abstract: Machine learning has achieved impressive performance in tomographic reconstruction, but supervised training requires paired measurements and ground-truth images that are often unavailable. This has motivated self-supervised approaches, which have primarily addressed denoising and, more recently, linear inverse problems. We address nonlinear inverse problems and introduce SPLIT (Self-supervised Partitioning for Learned Inversion in Nonlinear Tomography), a self-supervised machine-learning framework for reconstructing images from nonlinear, incomplete, and noisy projection data without any samples of ground-truth images. SPLIT enforces cross-partition consistency and measurement-domain fidelity while exploiting complementary information across multiple partitions. Our main theoretical result shows that, under mild conditions, the proposed self-supervised objective is equivalent to its supervised counterpart in expectation. We regularize training with an automatic stopping rule that halts optimization when a no-reference image-quality surrogate saturates. As a concrete application, we derive SPLIT variants for multispectral computed tomography. Experiments on sparse-view acquisitions demonstrate high reconstruction quality and robustness to noise, surpassing classical iterative reconstruction and recent self-supervised baselines.

Related

• Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse
• RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation
• Do Instance Priors Help Weakly Supervised Semantic Segmentation?
• FDIF: Formula-Driven supervised Learning with Implicit Functions for 3D Medical Image Segmentation
• Weakly-Supervised Lung Nodule Segmentation via Training-Free Guidance of 3D Rectified Flow

Source: arXiv cs.CV | 2026-04-20