Uformer-ICS: A U-Shaped Transformer for Image Compressive Sensing Service

TL;DR

Uformer-ICS introduces a U-shaped transformer architecture tailored for image compressive sensing, incorporating adaptive sampling and projection modules to enhance reconstruction quality at low sampling rates.

Contribution

The paper presents a novel U-shaped transformer with adaptive sampling and a multi-channel projection module, improving image reconstruction in compressive sensing tasks.

Findings

Outperforms state-of-the-art deep learning CS methods.

Effectively utilizes local and long-range image features.

Achieves superior reconstruction at low sampling rates.

Abstract

Many service computing applications require real-time dataset collection from multiple devices, necessitating efficient sampling techniques to reduce bandwidth and storage pressure. Compressive sensing (CS) has found wide-ranging applications in image acquisition and reconstruction. Recently, numerous deep-learning methods have been introduced for CS tasks. However, the accurate reconstruction of images from measurements remains a significant challenge, especially at low sampling rates. In this paper, we propose Uformer-ICS as a novel U-shaped transformer for image CS tasks by introducing inner characteristics of CS into transformer architecture. To utilize the uneven sparsity distribution of image blocks, we design an adaptive sampling architecture that allocates measurement resources based on the estimated block sparsity, allowing the compressed results to retain maximum information from the original image. Additionally, we introduce a multi-channel projection (MCP) module inspired by traditional CS optimization methods. By integrating the MCP module into the transformer blocks, we construct projection-based transformer blocks, and then form a symmetrical reconstruction model using these blocks and residual convolutional blocks. Therefore, our reconstruction model can simultaneously utilize the local features and long-range dependencies of image, and the prior projection knowledge of CS theory. Experimental results demonstrate its significantly better reconstruction performance than state-of-the-art deep learning-based CS methods.