Dynamic Path-Controllable Deep Unfolding Network for Compressive Sensing

TL;DR

This paper introduces DPC-DUN, a flexible deep unfolding network for compressive sensing that dynamically adjusts its processing path for each image, balancing reconstruction quality and computational efficiency.

Contribution

It proposes a novel dynamic path-controllable mechanism in deep unfolding networks, enabling adaptive tradeoffs between performance and complexity in CS reconstruction.

Findings

DPC-DUN achieves high flexibility and performance in CS tasks.

The method effectively balances accuracy and computational cost.

Extensive experiments validate the adaptability and efficiency of DPC-DUN.

Abstract

Deep unfolding network (DUN) that unfolds the optimization algorithm into a deep neural network has achieved great success in compressive sensing (CS) due to its good interpretability and high performance. Each stage in DUN corresponds to one iteration in optimization. At the test time, all the sampling images generally need to be processed by all stages, which comes at a price of computation burden and is also unnecessary for the images whose contents are easier to restore. In this paper, we focus on CS reconstruction and propose a novel Dynamic Path-Controllable Deep Unfolding Network (DPC-DUN). DPC-DUN with our designed path-controllable selector can dynamically select a rapid and appropriate route for each image and is slimmable by regulating different performance-complexity tradeoffs. Extensive experiments show that our DPC-DUN is highly flexible and can provide excellent performance and dynamic adjustment to get a suitable tradeoff, thus addressing the main requirements to become appealing in practice. Codes are available at https://github.com/songjiechong/DPC-DUN.