Meta-INR: Efficient Encoding of Volumetric Data via Meta-Learning Implicit Neural Representation
This work addresses the problem of efficient encoding of volumetric data for researchers and practitioners working with large-scale time-varying or ensemble volumetric datasets, offering an incremental solution.
The authors tackled the problem of inefficient optimization of implicit neural representation (INR) networks for volumetric data, achieving significantly faster convergence with just a few gradient updates. Meta-INR enables effective extraction of high-quality generalizable features for encoding unseen similar volume data.
Implicit neural representation (INR) has emerged as a promising solution for encoding volumetric data, offering continuous representations and seamless compatibility with the volume rendering pipeline. However, optimizing an INR network from randomly initialized parameters for each new volume is computationally inefficient, especially for large-scale time-varying or ensemble volumetric datasets where volumes share similar structural patterns but require independent training. To close this gap, we propose Meta-INR, a pretraining strategy adapted from meta-learning algorithms to learn initial INR parameters from partial observation of a volumetric dataset. Compared to training an INR from scratch, the learned initial parameters provide a strong prior that enhances INR generalizability, allowing significantly faster convergence with just a few gradient updates when adapting to a new volume and better interpretability when analyzing the parameters of the adapted INRs. We demonstrate that Meta-INR can effectively extract high-quality generalizable features that help encode unseen similar volume data across diverse datasets. Furthermore, we highlight its utility in tasks such as simulation parameter analysis and representative timestep selection. The code is available at https://github.com/spacefarers/MetaINR.