Introduces three algorithms for DIP early stopping via pseudo self-referenced images that outperform prior methods on natural and medical images under varying noise.
Solving inverse problems using data-driven models in medical imaging.Acta Numerica, 28:1–174, 2019
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A Principled Self-Referenced Early Stopping Approach for Deep Image Prior
Introduces three algorithms for DIP early stopping via pseudo self-referenced images that outperform prior methods on natural and medical images under varying noise.