Towards Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization
This work addresses practical issues in applying untrained network priors for image reconstruction, making them more efficient and accessible, though it is incremental in improving existing methods.
The paper tackled the challenges of untrained network priors in image reconstruction, such as architectural dependencies and overfitting, by proposing frequency regularization techniques that reduce the need for extensive tuning and achieve similar or superior performance with more compact models, as demonstrated on an MRI reconstruction task.
Untrained networks inspired by deep image priors have shown promising capabilities in recovering high-quality images from noisy or partial measurements without requiring training sets. Their success is widely attributed to implicit regularization due to the spectral bias of suitable network architectures. However, the application of such network-based priors often entails superfluous architectural decisions, risks of overfitting, and lengthy optimization processes, all of which hinder their practicality. To address these challenges, we propose efficient architecture-agnostic techniques to directly modulate the spectral bias of network priors: 1) bandwidth-constrained input, 2) bandwidth-controllable upsamplers, and 3) Lipschitz-regularized convolutional layers. We show that, with just a few lines of code, we can reduce overfitting in underperforming architectures and close performance gaps with high-performing counterparts, minimizing the need for extensive architecture tuning. This makes it possible to employ a more compact model to achieve performance similar or superior to larger models while reducing runtime. Demonstrated on inpainting-like MRI reconstruction task, our results signify for the first time that architectural biases, overfitting, and runtime issues of untrained network priors can be simultaneously addressed without architectural modifications. Our code is publicly available.