Image Super-Resolution via Dual-State Recurrent Networks
This work addresses image super-resolution for computer vision applications, presenting an incremental improvement over existing deep learning architectures.
The paper tackles image super-resolution by proposing a dual-state recurrent network (DSRN) that jointly exploits low-resolution and high-resolution signals with bidirectional recurrent feedback, achieving favorable performance in memory consumption and predictive accuracy compared to state-of-the-art methods.
Advances in image super-resolution (SR) have recently benefited significantly from rapid developments in deep neural networks. Inspired by these recent discoveries, we note that many state-of-the-art deep SR architectures can be reformulated as a single-state recurrent neural network (RNN) with finite unfoldings. In this paper, we explore new structures for SR based on this compact RNN view, leading us to a dual-state design, the Dual-State Recurrent Network (DSRN). Compared to its single state counterparts that operate at a fixed spatial resolution, DSRN exploits both low-resolution (LR) and high-resolution (HR) signals jointly. Recurrent signals are exchanged between these states in both directions (both LR to HR and HR to LR) via delayed feedback. Extensive quantitative and qualitative evaluations on benchmark datasets and on a recent challenge demonstrate that the proposed DSRN performs favorably against state-of-the-art algorithms in terms of both memory consumption and predictive accuracy.