Invertible Diffusion Models for Compressed Sensing

arXiv:2403.17006v1 Announce Type: new
Abstract: While deep neural networks (NN) significantly advance image compressed sensing (CS) by improving reconstruction quality, the necessity of training current CS NNs from scratch constrains their effectiveness and hampers rapid deployment. Although recent methods utilize pre-trained diffusion models for image reconstruction, they struggle with slow inference and restricted adaptability to CS. To tackle these challenges, this paper proposes Invertible Diffusion Models (IDM), a novel efficient, end-to-end diffusion-based CS method. IDM repurposes a large-scale diffusion sampling …

abstract adaptability advance arxiv cs.cv current deployment diffusion diffusion models image improving inference networks neural networks nns quality scratch sensing struggle training type