One-Two-One Networks for Compression Artifacts Reduction in Remote Sensing
arXiv:1804.00256 · doi:10.1016/j.isprsjprs.2018.01.003
Abstract
Compression artifacts reduction (CAR) is a challenging problem in the field of remote sensing. Most recent deep learning based methods have demonstrated superior performance over the previous hand-crafted methods. In this paper, we propose an end-to-end one-two-one (OTO) network, to combine different deep models, i.e., summation and difference models, to solve the CAR problem. Particularly, the difference model motivated by the Laplacian pyramid is designed to obtain the high frequency information, while the summation model aggregates the low frequency information. We provide an in-depth investigation into our OTO architecture based on the Taylor expansion, which shows that these two kinds of information can be fused in a nonlinear scheme to gain more capacity of handling complicated image compression artifacts, especially the blocking effect in compression. Extensive experiments are conducted to demonstrate the superior performance of the OTO networks, as compared to the state-of-the-arts on remote sensing datasets and other benchmark datasets.
References in corpus (9)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Fully Convolutional Networks for Semantic Segmentation
- Remote Sensing Image Scene Classification: Benchmark and State of the Art
- FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising
- A Survey on Object Detection in Optical Remote Sensing Images
- Compression Artifacts Removal Using Convolutional Neural Networks
- Deep Convolution Networks for Compression Artifacts Reduction