# RR-DnCNN v2.0: Enhanced Restoration-Reconstruction Deep Neural Network for Down-Sampling Based Video Coding

arXiv: https://arxiv.org/abs/2002.10739 · HTML: https://mlsanity.com/paper/2002.10739/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Feb 2020.

## Built on by (most cited first, 5 of 5)

- [Reference-Guided Texture and Structure Inference for Image Inpainting](https://mlsanity.com/paper/2207.14498/) (2022)
- [TransRef: Multi-Scale Reference Embedding Transformer for Reference-Guided Image Inpainting](https://mlsanity.com/paper/2306.11528/) (2023)
- [SR+Codec: a Benchmark of Super-Resolution for Video Compression Bitrate Reduction](https://mlsanity.com/paper/2305.04844/) (2023)
- [Video Compression with Arbitrary Rescaling Network](https://mlsanity.com/paper/2306.04202/) (2023)
- [CNN-based TEM image denoising from first principles](https://mlsanity.com/paper/2501.11225/) (2025)

## Abstract (arXiv)

Integrating deep learning techniques into the video coding framework gains significant improvement compared to the standard compression techniques, especially applying super-resolution (up-sampling) to down-sampling based video coding as post-processing. However, besides up-sampling degradation, the various artifacts brought from compression make super-resolution problem more difficult to solve. The straightforward solution is to integrate the artifact removal techniques before super-resolution. However, some helpful features may be removed together, degrading the super-resolution performance. To address this problem, we proposed an end-to-end restoration-reconstruction deep neural network (RR-DnCNN) using the degradation-aware technique, which entirely solves degradation from compression and sub-sampling. Besides, we proved that the compression degradation produced by Random Access configuration is rich enough to cover other degradation types, such as Low Delay P and All Intra, for training. Since the straightforward network RR-DnCNN with many layers as a chain has poor learning capability suffering from the gradient vanishing problem, we redesign the network architecture to let reconstruction leverages the captured features from restoration using up-sampling skip connections. Our novel architecture is called restoration-reconstruction u-shaped deep neural network (RR-DnCNN v2.0). As a result, our RR-DnCNN v2.0 outperforms the previous works and can attain 17.02% BD-rate reduction on UHD resolution for all-intra anchored by the standard H.265/HEVC. The source code is available at https://minhmanho.github.io/rrdncnn/.