Efficient Single Image Super Resolution using Enhanced Learned Group Convolutions
This work addresses the need for more efficient super-resolution models for applications requiring real-time or low-resource processing, though it is incremental as it builds on existing CondenseNet architecture.
The paper tackles the problem of single-image super-resolution by proposing a computationally efficient CNN method, SRCondenseNet, which reduces computations by using enhanced learned group convolutions and removing unnecessary modules, achieving competitive accuracy against state-of-the-art methods.
Convolutional Neural Networks (CNNs) have demonstrated great results for the single-image super-resolution (SISR) problem. Currently, most CNN algorithms promote deep and computationally expensive models to solve SISR. However, we propose a novel SISR method that uses relatively less number of computations. On training, we get group convolutions that have unused connections removed. We have refined this system specifically for the task at hand by removing unnecessary modules from original CondenseNet. Further, a reconstruction network consisting of deconvolutional layers has been used in order to upscale to high resolution. All these steps significantly reduce the number of computations required at testing time. Along with this, bicubic upsampled input is added to the network output for easier learning. Our model is named SRCondenseNet. We evaluate the method using various benchmark datasets and show that it performs favourably against the state-of-the-art methods in terms of both accuracy and number of computations required.