Hrnet: Hamiltonian Rescaling Network for Image Downscaling

Image downscaling has become a classical problem in image processing and has recently connected to image super-resolution (SR), which restores high-quality images from low-resolution ones generated by predetermined downscaling kernels (e.g., bicubic). However, most existing image downscaling methods are deterministic and lose information during the downscaling process, while rarely designing specific downscaling methods for image SR. In this paper, we propose a novel learning-based image downscaling method, Hamiltonian Rescaling Network (HRNet). The design of HRNet is based on the discretization of Hamiltonian System, a pair of iterative updating equations, which formulate a mechanism of iterative correction of the error caused by information missing during image or feature downscaling. Extensive experiments demonstrate the effectiveness of our proposed method in terms of both quantitative and qualitative results.

[1]  Bin Dong,et al.  Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations , 2017, ICML.

[2]  Michael Elad,et al.  On Single Image Scale-Up Using Sparse-Representations , 2010, Curves and Surfaces.

[3]  Yunjin Chen,et al.  Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image Restoration , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Kyoung Mu Lee,et al.  Task-Aware Image Downscaling , 2018, ECCV.

[5]  Aline Roumy,et al.  Low-Complexity Single-Image Super-Resolution based on Nonnegative Neighbor Embedding , 2012, BMVC.

[6]  Houqiang Li,et al.  Learning a Convolutional Neural Network for Image Compact-Resolution , 2019, IEEE Transactions on Image Processing.

[7]  Yun Fu,et al.  Image Super-Resolution Using Very Deep Residual Channel Attention Networks , 2018, ECCV.

[8]  Eirikur Agustsson,et al.  NTIRE 2017 Challenge on Single Image Super-Resolution: Dataset and Study , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[9]  Shu-Tao Xia,et al.  Second-Order Attention Network for Single Image Super-Resolution , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[10]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[11]  Uri M. Ascher,et al.  Computer methods for ordinary differential equations and differential-algebraic equations , 1998 .

[12]  Arun N. Netravali,et al.  Reconstruction filters in computer-graphics , 1988, SIGGRAPH.

[13]  Jitendra Malik,et al.  A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[14]  Eldad Haber,et al.  Reversible Architectures for Arbitrarily Deep Residual Neural Networks , 2017, AAAI.

[15]  Kyoung Mu Lee,et al.  Enhanced Deep Residual Networks for Single Image Super-Resolution , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).

[16]  A. M. Lyapunov.  The general problem of the stability of motion , 1992 .

[17]  Gregory Shakhnarovich,et al.  Deep Back-Projection Networks for Super-Resolution , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[18]  Bin Dong,et al.  Dynamically Unfolding Recurrent Restorer: A Moving Endpoint Control Method for Image Restoration , 2018, ICLR.

[19]  C. Duchon.  Lanczos Filtering in One and Two Dimensions , 1979 .

[20]  Pieter Peers,et al.  Content-adaptive image downscaling , 2013, ACM Trans. Graph..