Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections
read the original abstract
Image restoration, including image denoising, super resolution, inpainting, and so on, is a well-studied problem in computer vision and image processing, as well as a test bed for low-level image modeling algorithms. In this work, we propose a very deep fully convolutional auto-encoder network for image restoration, which is a encoding-decoding framework with symmetric convolutional-deconvolutional layers. In other words, the network is composed of multiple layers of convolution and de-convolution operators, learning end-to-end mappings from corrupted images to the original ones. The convolutional layers capture the abstraction of image contents while eliminating corruptions. Deconvolutional layers have the capability to upsample the feature maps and recover the image details. To deal with the problem that deeper networks tend to be more difficult to train, we propose to symmetrically link convolutional and deconvolutional layers with skip-layer connections, with which the training converges much faster and attains better results.
This paper has not been read by Pith yet.
Forward citations
Cited by 4 Pith papers
-
Deep Learned Optical Multiplexing for Multi-Focal Plane Microscopy
Joint optimization of an LED pattern and neural network allows extraction of five focal planes from a single multiplexed image in live microscopy.
-
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Progressive growing stabilizes GAN training to produce high-resolution images of unprecedented quality and achieves a record unsupervised inception score of 8.80 on CIFAR10.
-
Coupled-Projection Residual Network for MRI Super-Resolution
A new dual-path neural network architecture called CPRN with coupled-projection feedback and step-wise feature fusion outperforms prior methods for MRI super-resolution on three public datasets.
-
Image Super-Resolution Using Attention Based DenseNet with Residual Deconvolution
ADRD is an attention-based DenseNet variant with residual deconvolution that reports improved quantitative and qualitative super-resolution results on public datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.