# DynaVSR: Dynamic Adaptive Blind Video Super-Resolution

arXiv: https://arxiv.org/abs/2011.04482 · HTML: https://mlsanity.com/paper/2011.04482/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Nov 2020.

## Built on by (most cited first, 10 of 10)

- [Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling](https://mlsanity.com/paper/2204.07114/) (2022)
- [Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric](https://mlsanity.com/paper/2203.08923/) (2022)
- [A Survey of Deep Learning Video Super-Resolution](https://mlsanity.com/paper/2506.03216/) (2025)
- [Ada-VSR: Adaptive Video Super-Resolution with Meta-Learning](https://mlsanity.com/paper/2108.02832/) (2021)
- [Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization](https://mlsanity.com/paper/2508.18859/) (2025)
- [Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolution](https://mlsanity.com/paper/2212.14046/) (2022)
- [Self-Supervised Adaptation for Video Super-Resolution](https://mlsanity.com/paper/2103.10081/) (2021)
- [3DHR-Co: A Collaborative Test-time Refinement Framework for In-the-Wild 3D Human-Body Reconstruction Task](https://mlsanity.com/paper/2310.01291/) (2023)
- [FCA2: Frame Compression-Aware Autoencoder for Modular and Fast Compressed Video Super-Resolution](https://mlsanity.com/paper/2506.11545/) (2025)
- [FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring](https://mlsanity.com/paper/2512.04390/) (2025)

## Abstract (arXiv)

Most conventional supervised super-resolution (SR) algorithms assume that low-resolution (LR) data is obtained by downscaling high-resolution (HR) data with a fixed known kernel, but such an assumption often does not hold in real scenarios. Some recent blind SR algorithms have been proposed to estimate different downscaling kernels for each input LR image. However, they suffer from heavy computational overhead, making them infeasible for direct application to videos. In this work, we present DynaVSR, a novel meta-learning-based framework for real-world video SR that enables efficient downscaling model estimation and adaptation to the current input. Specifically, we train a multi-frame downscaling module with various types of synthetic blur kernels, which is seamlessly combined with a video SR network for input-aware adaptation. Experimental results show that DynaVSR consistently improves the performance of the state-of-the-art video SR models by a large margin, with an order of magnitude faster inference time compared to the existing blind SR approaches.