2023/07/01 by Jeevan, Pranav, Srinidhi, Akella, Prathiba, Pasunuri +1 · 2 citations
#Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #I.2.10 #I.4.0 #I.4.1 #I.4.10 #I.4.2 #I.4.3 #I.4.4 #I.4.5 #I.4.6 #I.4.7 #I.4.8 #I.4.9 #I.5.1 #I.5.2 #I.5.4
paper · doi:10.48550/arxiv.2307.00430
Image super-resolution research recently been dominated by transformer models which need higher computational resources than CNNs due to the quadratic complexity of self-attention. We propose a new neural network -- WaveMixSR -- for image super-resolution based on WaveMix architecture which uses a 2D-discrete wavelet transform for spatial token-mixing. Unlike transformer-based models, WaveMixSR does not unroll the image as a sequence of pixels/patches. It uses the inductive bias of convolutions along with the lossless token-mixing property of wavelet transform to achieve higher performance while requiring fewer resources and training data. We compare the performance of our network with other state-of-the-art methods for image super-resolution. Our experiments show that WaveMixSR achieves competitive performance in all datasets and reaches state-of-the-art performance in the BSD100 dataset on multiple super-resolution tasks. Our model is able to achieve this performance using less training data and computational resources while maintaining high parameter efficiency compared to current state-of-the-art models.