Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution

Citations Over TimeTop 1% of 2017 papers

Abstract

Convolutional neural networks have recently demonstrated high-quality reconstruction for single-image super-resolution. In this paper, we propose the Laplacian Pyramid Super-Resolution Network (LapSRN) to progressively reconstruct the sub-band residuals of high-resolution images. At each pyramid level, our model takes coarse-resolution feature maps as input, predicts the high-frequency residuals, and uses transposed convolutions for upsampling to the finer level. Our method does not require the bicubic interpolation as the pre-processing step and thus dramatically reduces the computational complexity. We train the proposed LapSRN with deep supervision using a robust Charbonnier loss function and achieve high-quality reconstruction. Furthermore, our network generates multi-scale predictions in one feed-forward pass through the progressive reconstruction, thereby facilitates resource-aware applications. Extensive quantitative and qualitative evaluations on benchmark datasets show that the proposed algorithm performs favorably against the state-of-the-art methods in terms of speed and accuracy.

Related Papers

• → ASFlow: Unsupervised Optical Flow Learning With Adaptive Pyramid Sampling(2021)16 cited
• → An Optimization Method for Video Upsampling and Downsampling Using Interpolation-Dependent Image Downsampling(2021)4 cited
• → Degradation Reconstruction Loss: A Perceptual-Oriented Super-Resolution Framework for Multi-downsampling Degradations(2021)2 cited
• → ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling(2021)