A. Meyer-Baese

MRIComp4Flow: Compression of 3D Brain MRI for Training Multi-Modal Generative Models

Large-scale multi-modal MRI datasets impose substantial storage and I/O costs, limiting the training of 3D generative models on commodity infrastructure. While lossy compression is known to preserve accuracy for discriminative segmentation networks, its effect on generative models, which must learn the full data distri...