Locally-Supervised Global Image Restoration
This addresses the problem of reducing ground truth data requirements for image restoration in applications like medical imaging, though it appears incremental as it builds on existing self-supervised frameworks.
The paper tackles image reconstruction from incomplete measurements, such as upsampling and inpainting, by using a learning-based method that exploits multiple invariances to achieve performance comparable to fully supervised approaches with less ground truth data, as validated on photoacoustic microscopy upsampling with competitive or superior results.
We address the problem of image reconstruction from incomplete measurements, encompassing both upsampling and inpainting, within a learning-based framework. Conventional supervised approaches require fully sampled ground truth data, while self-supervised methods allow incomplete ground truth but typically rely on random sampling that, in expectation, covers the entire image. In contrast, we consider fixed, deterministic sampling patterns with inherently incomplete coverage, even in expectation. To overcome this limitation, we exploit multiple invariances of the underlying image distribution, which theoretically allows us to achieve the same reconstruction performance as fully supervised approaches. We validate our method on optical-resolution image upsampling in photoacoustic microscopy (PAM), demonstrating competitive or superior results while requiring substantially less ground truth data.