# Restore from Restored: Video Restoration with Pseudo Clean Video

arXiv: https://arxiv.org/abs/2003.04279 · HTML: https://mlsanity.com/paper/2003.04279/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2020.

## Built on by (most cited first, 11 of 11)

- [VRT: A Video Restoration Transformer](https://mlsanity.com/paper/2201.12288/) (2022)
- [A Comparison of Image Denoising Methods](https://mlsanity.com/paper/2304.08990/) (2023)
- [Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers](https://mlsanity.com/paper/2409.11256/) (2024)
- [Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising](https://mlsanity.com/paper/2208.11803/) (2022)
- [Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable](https://mlsanity.com/paper/2504.03136/) (2025)
- [Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques](https://mlsanity.com/paper/2507.08375/) (2025)
- [Subspace modeling for fast and high-sensitivity X-ray chemical imaging](https://mlsanity.com/paper/2201.00259/) (2022)
- [Towards Real-World Video Denosing: A Practical Video Denosing Dataset and Network](https://mlsanity.com/paper/2207.01356/) (2022)
- [3DHR-Co: A Collaborative Test-time Refinement Framework for In-the-Wild 3D Human-Body Reconstruction Task](https://mlsanity.com/paper/2310.01291/) (2023)
- [Reimagining Reality: A Comprehensive Survey of Video Inpainting Techniques](https://mlsanity.com/paper/2401.17883/) (2024)
- [Frames2Residual: Spatiotemporal Decoupling for Self-Supervised Video Denoising](https://mlsanity.com/paper/2603.10417/) (2026)

## Abstract (arXiv)

In this study, we propose a self-supervised video denoising method called "restore-from-restored." This method fine-tunes a pre-trained network by using a pseudo clean video during the test phase. The pseudo clean video is obtained by applying a noisy video to the baseline network. By adopting a fully convolutional neural network (FCN) as the baseline, we can improve video denoising performance without accurate optical flow estimation and registration steps, in contrast to many conventional video restoration methods, due to the translation equivariant property of the FCN. Specifically, the proposed method can take advantage of plentiful similar patches existing across multiple consecutive frames (i.e., patch-recurrence); these patches can boost the performance of the baseline network by a large margin. We analyze the restoration performance of the fine-tuned video denoising networks with the proposed self-supervision-based learning algorithm, and demonstrate that the FCN can utilize recurring patches without requiring accurate registration among adjacent frames. In our experiments, we apply the proposed method to state-of-the-art denoisers and show that our fine-tuned networks achieve a considerable improvement in denoising performance.