Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution
Authors:
Preprint
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.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Holistically-Nested Edge DetectionInternational Journal of Computer Vision, 2017
- Learning to Refine Object Segments2016
- Accelerating the Super-Resolution Convolutional Neural Network2016
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation2016
- A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution2015
- Super-Resolution Using Sub-Band Self-Similarity2015
- Single-Image Super-Resolution: A Benchmark2014
- Lucas/Kanade Meets Horn/Schunck: Combining Local and Global Optic Flow MethodsInternational Journal of Computer Vision, 2005
- Example-based super-resolutionIEEE Computer Graphics and Applications, 2002