# Image Restoration Using Convolutional Auto-encoders with Symmetric Skip Connections

arXiv: https://arxiv.org/abs/1606.08921 · HTML: https://mlsanity.com/paper/1606.08921/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jun 2016.

## Built on by (most cited first, 30 of 30)

- [Just Noticeable Difference for Deep Machine Vision](https://mlsanity.com/paper/2102.08168/) (2021)
- [High-dimensional Asymptotics of Denoising Autoencoders](https://mlsanity.com/paper/2305.11041/) (2023)
- [FingerGAN: A Constrained Fingerprint Generation Scheme for Latent Fingerprint Enhancement](https://mlsanity.com/paper/2206.12885/) (2022)
- [High-Resolution Pelvic MRI Reconstruction Using a Generative Adversarial Network with Attention and Cyclic Loss](https://mlsanity.com/paper/2107.09989/) (2021)
- [HDR Imaging with Spatially Varying Signal-to-Noise Ratios](https://mlsanity.com/paper/2303.17253/) (2023)
- [Deep neural networks-based denoising models for CT imaging and their efficacy](https://mlsanity.com/paper/2111.09539/) (2021)
- [What do we learn? Debunking the Myth of Unsupervised Outlier Detection](https://mlsanity.com/paper/2206.03698/) (2022)
- [Latent space configuration for improved generalization in supervised autoencoder neural networks](https://mlsanity.com/paper/2402.08441/) (2024)
- [Condition-Invariant and Compact Visual Place Description by Convolutional Autoencoder](https://mlsanity.com/paper/2204.07350/) (2022)
- [textitFastSVD-ML-ROM: A Reduced-Order Modeling Framework based on Machine Learning for Real-Time Applications](https://mlsanity.com/paper/2207.11842/) (2022)
- [Integrating Deep Reinforcement and Supervised Learning to Expedite Indoor Mapping](https://mlsanity.com/paper/2109.08490/) (2021)
- [Blind microscopy image denoising with a deep residual and multiscale encoder/decoder network](https://mlsanity.com/paper/2105.00273/) (2021)
- [Compound Multi-branch Feature Fusion for Real Image Restoration](https://mlsanity.com/paper/2206.02748/) (2022)
- [SwinFuSR: an image fusion-inspired model for RGB-guided thermal image super-resolution](https://mlsanity.com/paper/2404.14533/) (2024)
- [Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers](https://mlsanity.com/paper/2510.27211/) (2025)
- [ChaLearn Looking at People: Inpainting and Denoising challenges](https://mlsanity.com/paper/2106.13071/) (2021)
- [DeepA: A Deep Neural Analyzer For Speech And Singing Vocoding](https://mlsanity.com/paper/2110.06434/) (2021)
- [DriveGuard: Robustification of Automated Driving Systems with Deep Spatio-Temporal Convolutional Autoencoder](https://mlsanity.com/paper/2111.03480/) (2021)
- [A Possible Converter to Denoise the Images of Exoplanet Candidates through Machine Learning Techniques](https://mlsanity.com/paper/2301.04292/) (2023)
- [Adaptation of the super resolution SOTA for Art Restoration in camera capture images](https://mlsanity.com/paper/2309.13655/) (2023)
- [Climate Downscaling: A Deep-Learning Based Super-resolution Model of Precipitation Data with Attention Block and Skip Connections](https://mlsanity.com/paper/2403.17847/) (2024)
- [Assessing the performance of CT image denoisers using Laguerre-Gauss Channelized Hotelling Observer for lesion detection](https://mlsanity.com/paper/2412.02920/) (2024)
- [Advances in Electron Microscopy with Deep Learning](https://mlsanity.com/paper/2101.01178/) (2021)
- [Modeling Graph Node Correlations with Neighbor Mixture Models](https://mlsanity.com/paper/2103.15966/) (2021)
- [Visual Time Series Forecasting: An Image-driven Approach](https://mlsanity.com/paper/2107.01273/) (2021)
- [Unsupervised Learning for Target Tracking and Background Subtraction in Satellite Imagery](https://mlsanity.com/paper/2109.00885/) (2021)
- [Speckle Image Restoration without Clean Data](https://mlsanity.com/paper/2205.08833/) (2022)
- [Ladder Bottom-up Convolutional Bidirectional Variational Autoencoder for Image Translation of Dotted Arabic Expiration Dates](https://mlsanity.com/paper/2310.14069/) (2023)
- [FFAD: A Novel Metric for Assessing Generated Time Series Data Utilizing Fourier Transform and Auto-encoder](https://mlsanity.com/paper/2403.06576/) (2024)
- [Reference-Free Image Quality Metric for Degradation and Reconstruction Artifacts](https://mlsanity.com/paper/2405.02208/) (2024)

## Abstract (arXiv)

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.