A DEM Super-Resolution Reconstruction Network Combining Internal and External Learning
نویسندگان
چکیده
The study of digital elevation model (DEM) super-resolution reconstruction algorithms has solved the problem need for high-resolution DEMs. However, DEM algorithm itself is an inverse problem, and making full use a priori information effective way to solve this problem. In our work, new method proposed based on complementary relationship between internally learned methods externally methods. presence large amount repetitive within DEM. Using internal learning approach learn prior DEM, low-resolution dataset rich in detailed features generated, this, training constrained external network constructed discrepancy data pair. Finally, it introduces residual accelerate operation rate degradation brought about by deepening network. This enables better transfer deeper mappings, which turn ensures accurate information. utilizes specific as well achieves results experimental results. Bicubic method, Super-Resolution Convolutional Neural Networks (SRCNN), very deep convolutional networks (VDSR), ”Zero-Shot” (ZSSR) paper were compared, average RMSE five 8.48 m, 8.30 8.09 7.02 m 6.65 respectively. mean error at same resolution 21.6% than that 19.9% SRCNN, 17.8% VDSR 5.3% ZSSR method.
منابع مشابه
A Novel Super Resolution Reconstruction
Due to the factors like processing power limitations and channel capabilities images are often down sampled and transmitted at low bit rates resulting in a low resolution compressed image. High resolution images can be reconstructed from several blurred, noisy and down sampled low resolution images using a computational process know as super resolution reconstruction. Super-resolution is the pr...
متن کامل"Zero-Shot" Super-Resolution using Deep Internal Learning
Deep Learning has led to a dramatic leap in SuperResolution (SR) performance in the past few years. However, being supervised, these SR methods are restricted to specific training data, where the acquisition of the lowresolution (LR) images from their high-resolution (HR) counterparts is predetermined (e.g., bicubic downscaling), without any distracting artifacts (e.g., sensor noise, image comp...
متن کاملLearning a Single Convolutional Super-Resolution Network for Multiple Degradations
Recent years have witnessed the unprecedented success of deep convolutional neural networks (CNNs) in single image super-resolution (SISR). However, existing CNN-based SISR methods mostly assume that a low-resolution (LR) image is bicubicly downsampled from a high-resolution (HR) image, thus inevitably giving rise to poor performance when the true degradation does not follow this assumption. Mo...
متن کاملLearning a Deep Convolutional Network for Image Super-Resolution
We propose a deep learning method for single image superresolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) [15] that takes the lowresolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also ...
متن کاملImage Super-Resolution Reconstruction Based On Multi-Dictionary Learning
In order to overcome the problems that the single dictionary cannot be adapted to variety types of images and the reconstruction quality couldn’t meet the application, we propose a novel Multi-Dictionary Learning algorithm for feature classification. The algorithm uses the orientation information of the low resolution image to guide the image patches in the database to classify, and designs the...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Remote Sensing
سال: 2022
ISSN: ['2315-4632', '2315-4675']
DOI: https://doi.org/10.3390/rs14092181