Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Fast and Accurate Image Super-Resolution with Deep Laplacian Pyramid Networks

About

Convolutional neural networks have recently demonstrated high-quality reconstruction for single image super-resolution. However, existing methods often require a large number of network parameters and entail heavy computational loads at runtime for generating high-accuracy super-resolution results. In this paper, we propose the deep Laplacian Pyramid Super-Resolution Network for fast and accurate image super-resolution. The proposed network progressively reconstructs the sub-band residuals of high-resolution images at multiple pyramid levels. In contrast to existing methods that involve the bicubic interpolation for pre-processing (which results in large feature maps), the proposed method directly extracts features from the low-resolution input space and thereby entails low computational loads. We train the proposed network with deep supervision using the robust Charbonnier loss functions and achieve high-quality image reconstruction. Furthermore, we utilize the recursive layers to share parameters across as well as within pyramid levels, and thus drastically reduce the number of parameters. 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 run-time and image quality.

Wei-Sheng Lai, Jia-Bin Huang, Narendra Ahuja, Ming-Hsuan Yang• 2017

Related benchmarks

TaskDatasetResultRank
Super-ResolutionSet5
PSNR26.34
751
Image Super-resolutionManga109
PSNR23.9
656
Single Image Super-ResolutionUrban100
PSNR22.06
500
Super-ResolutionB100
PSNR24.65
418
Single Image Super-ResolutionSet5
PSNR26.34
352
Image Super-resolutionSet14
PSNR24.57
289
Super-ResolutionSet5 x2
PSNR37.78
134
Super-ResolutionSet14 4x (test)
PSNR28.26
117
Super-ResolutionManga109 4x
PSNR29.54
88
Super-ResolutionManga109 2x
PSNR37.78
54
Showing 10 of 22 rows

Other info

Follow for update