NeTMY neural fields with annealed encoding, multiscale optimization, and spectrum-fidelity losses achieve superior localization and distributional accuracy in NV-center inverse sensing by using a tensor power-summed dipolar operator that exposes and mitigates center-collapse failures.
Understanding untrained deep models for inverse problems: Algorithms and theory
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
FMPlug adapts foundation flow-matching models into practical priors for inverse problems by combining instance-guided warm-start with sharp Gaussianity regularization, showing superior results on image restoration and scientific tasks with limited samples.
The method uses Smooth ℓ1 loss, divergence regularization, and input optimization in DIP to prevent overfitting and achieve better denoising on real HSIs with Gaussian, sparse, and stripe noise than prior DIP variants.
citing papers explorer
-
Neural Fields for NV-Center Inverse Sensing
NeTMY neural fields with annealed encoding, multiscale optimization, and spectrum-fidelity losses achieve superior localization and distributional accuracy in NV-center inverse sensing by using a tensor power-summed dipolar operator that exposes and mitigates center-collapse failures.
-
Saving Foundation Flow-Matching Priors for Inverse Problems
FMPlug adapts foundation flow-matching models into practical priors for inverse problems by combining instance-guided warm-start with sharp Gaussianity regularization, showing superior results on image restoration and scientific tasks with limited samples.
-
Preventing Overfitting in Deep Image Prior for Hyperspectral Image Denoising
The method uses Smooth ℓ1 loss, divergence regularization, and input optimization in DIP to prevent overfitting and achieve better denoising on real HSIs with Gaussian, sparse, and stripe noise than prior DIP variants.