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

نویسندگان

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

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.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A Deep Model for Super-resolution Enhancement from a Single Image

This study presents a method to reconstruct a high-resolution image using a deep convolution neural network. We propose a deep model, entitled Deep Block Super Resolution (DBSR), by fusing the output features of a deep convolutional network and a shallow convolutional network. In this way, our model benefits from high frequency and low frequency features extracted from deep and shallow networks...

متن کامل

Deep Inception-Residual Laplacian Pyramid Networks for Accurate Single Image Super-Resolution

With exploiting contextual information over large image regions in an efficient way, the deep convolutional neural network has shown an impressive performance for single image super-resolution (SR). In this paper, we propose a deep convolutional network by cascading the well-designed inception-residual blocks within the deep Laplacian pyramid framework to progressively restore the missing high-...

متن کامل

Deep Laplacian Pyramid Networks for Fast and Accurate Super-Resolution Supplementary Material

In this supplementary document, we present additional results to complement the paper. First, we provide the detailed configurations and parameters of the proposed LapSRN. Second, we show the comparisons with the network architecture of LAPGAN [3] and the adversarial loss training. We also provide analysis on different training datasets used in existing methods. Third, we present the run time e...

متن کامل

Super-Resolution Optical Flow

Existing approaches to super-resolution are not applicable to videos of faces because faces are non-planar, non-rigid, non-lambertian, and are subject to self occlusion. We present super-resolution optical ow as a solution to these problems. Super-resolution optical ow takes as input a conventional video stream, and simultaneously computes both optical ow and a super-resolution version of the e...

متن کامل

Joint convolutional neural pyramid for depth map super-resolution

High-resolution depth map can be inferred from a lowresolution one with the guidance of an additional highresolution texture map of the same scene. Recently, deep neural networks with large receptive fields are shown to benefit applications such as image completion. Our insight is that super resolution is similar to image completion, where only parts of the depth values are precisely known. In ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • CoRR

دوره abs/1710.01992  شماره 

صفحات  -

تاریخ انتشار 2017