A MAML-based pretraining strategy learns SIREN initial weights from under 1% of a volumetric dataset, enabling few-step adaptation to similar volumes with improved reconstruction quality and faster encoding.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Meta-INR: Efficient Encoding of Volumetric Data via Meta-Learning Implicit Neural Representation
A MAML-based pretraining strategy learns SIREN initial weights from under 1% of a volumetric dataset, enabling few-step adaptation to similar volumes with improved reconstruction quality and faster encoding.