U2-rPCA unfolds IRLS rPCA into an unsupervised network with a sparse-enhancement unit that is trained on part of an ultrasound sequence and applied to subsequent frames, showing CNR gains of 1.91-8.48 dB over SVD, rPCA, and supervised deep filters on in-silico and in-vivo data.
A total variation prior unrolling approach for computed tomography reconstruction,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Unsupervised Unfolded rPCA (U2-rPCA): Deep Interpretable Clutter Filtering for Ultrasound Microvascular Imaging
U2-rPCA unfolds IRLS rPCA into an unsupervised network with a sparse-enhancement unit that is trained on part of an ultrasound sequence and applied to subsequent frames, showing CNR gains of 1.91-8.48 dB over SVD, rPCA, and supervised deep filters on in-silico and in-vivo data.