Image Restoration from Patch-based Compressed Sensing Measurement
This addresses the problem of efficient and artifact-free image restoration for applications like compressed sensing and JPEG compression, though it is incremental as it builds on existing neural network approaches.
The paper tackles image reconstruction from patch-based compressed sensing measurements, which often suffers from blocky artifacts and high time complexity, by proposing a non-iterative method using cascaded residual convolutional networks that achieves state-of-the-art performance with low time cost.
A series of methods have been proposed to reconstruct an image from compressively sensed random measurement, but most of them have high time complexity and are inappropriate for patch-based compressed sensing capture, because of their serious blocky artifacts in the restoration results. In this paper, we present a non-iterative image reconstruction method from patch-based compressively sensed random measurement. Our method features two cascaded networks based on residual convolution neural network to learn the end-to-end full image restoration, which is capable of reconstructing image patches and removing the blocky effect with low time cost. Experimental results on synthetic and real data show that our method outperforms state-of-the-art compressive sensing (CS) reconstruction methods with patch-based CS measurement. To demonstrate the effectiveness of our method in more general setting, we apply the de-block process in our method to JPEG compression artifacts removal and achieve outstanding performance as well.