Learning Transferable Features for Implicit Neural Representations

TL;DR

This paper introduces STRAINER, a training framework for implicit neural representations that learns transferable features, enabling faster and higher-quality fitting of signals from similar domains, with improved initialization and generalization.

Contribution

The paper proposes a novel INR training method, STRAINER, that shares encoder layers to learn transferable features, enhancing signal fitting speed and quality across similar signals.

Findings

STRAINER achieves approximately +10dB signal quality gain early in training.

It provides effective initialization for fitting images from the same domain.

STRAINER improves transferability of learned neural features across signals.

Abstract

Implicit neural representations (INRs) have demonstrated success in a variety of applications, including inverse problems and neural rendering. An INR is typically trained to capture one signal of interest, resulting in learned neural features that are highly attuned to that signal. Assumed to be less generalizable, we explore the aspect of transferability of such learned neural features for fitting similar signals. We introduce a new INR training framework, STRAINER that learns transferrable features for fitting INRs to new signals from a given distribution, faster and with better reconstruction quality. Owing to the sequential layer-wise affine operations in an INR, we propose to learn transferable representations by sharing initial encoder layers across multiple INRs with independent decoder layers. At test time, the learned encoder representations are transferred as initialization for an otherwise randomly initialized INR. We find STRAINER to yield extremely powerful initialization for fitting images from the same domain and allow for $\approx +10dB$ gain in signal quality early on compared to an untrained INR itself. STRAINER also provides a simple way to encode data-driven priors in INRs. We evaluate STRAINER on multiple in-domain and out-of-domain signal fitting tasks and inverse problems and further provide detailed analysis and discussion on the transferability of STRAINER's features. Our demo can be accessed at https://kushalvyas.github.io/strainer.html .