# Scene-Adaptive Video Frame Interpolation via Meta-Learning

arXiv: https://arxiv.org/abs/2004.00779 · HTML: https://mlsanity.com/paper/2004.00779/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2020.

## Built on by (most cited first, 20 of 20)

- [CDFI: Compression-Driven Network Design for Frame Interpolation](https://mlsanity.com/paper/2103.10559/) (2021)
- [MetaHTR: Towards Writer-Adaptive Handwritten Text Recognition](https://mlsanity.com/paper/2104.01876/) (2021)
- [Splatting-based Synthesis for Video Frame Interpolation](https://mlsanity.com/paper/2201.10075/) (2022)
- [Adaptive Fine-Grained Sketch-Based Image Retrieval](https://mlsanity.com/paper/2207.01723/) (2022)
- [Test-Time Adaptation for Point Cloud Upsampling Using Meta-Learning](https://mlsanity.com/paper/2308.16484/) (2023)
- [Long-term Video Frame Interpolation via Feature Propagation](https://mlsanity.com/paper/2203.15427/) (2022)
- [Efficient Meta-Tuning for Content-aware Neural Video Delivery](https://mlsanity.com/paper/2207.09691/) (2022)
- [EA-Net: Edge-Aware Network for Flow-based Video Frame Interpolation](https://mlsanity.com/paper/2105.07673/) (2021)
- [Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2104.07473/) (2021)
- [Harnessing Meta-Learning for Improving Full-Frame Video Stabilization](https://mlsanity.com/paper/2403.03662/) (2024)
- [Learn to Adapt for Monocular Depth Estimation](https://mlsanity.com/paper/2203.14005/) (2022)
- [Beyond a Video Frame Interpolator: A Space Decoupled Learning Approach to Continuous Image Transition](https://mlsanity.com/paper/2203.09771/) (2022)
- [Meta-Auxiliary Network for 3D GAN Inversion](https://mlsanity.com/paper/2305.10884/) (2023)
- [Boost Video Frame Interpolation via Motion Adaptation](https://mlsanity.com/paper/2306.13933/) (2023)
- [Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization](https://mlsanity.com/paper/2508.18859/) (2025)
- [Human and Scene Motion Deblurring using Pseudo-blur Synthesizer](https://mlsanity.com/paper/2111.12911/) (2021)
- [Implicit View-Time Interpolation of Stereo Videos using Multi-Plane Disparities and Non-Uniform Coordinates](https://mlsanity.com/paper/2303.17181/) (2023)
- [Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification](https://mlsanity.com/paper/2406.14797/) (2024)
- [TVRN: Invertible Neural Networks for Compression-Aware Temporal Video Rescaling](https://mlsanity.com/paper/2605.15579/) (2026)
- [Learning to Recover Task Experts from a Multi-Task Merged Model](https://mlsanity.com/paper/2606.26902/) (2026)

## Abstract (arXiv)

Video frame interpolation is a challenging problem because there are different scenarios for each video depending on the variety of foreground and background motion, frame rate, and occlusion. It is therefore difficult for a single network with fixed parameters to generalize across different videos. Ideally, one could have a different network for each scenario, but this is computationally infeasible for practical applications. In this work, we propose to adapt the model to each video by making use of additional information that is readily available at test time and yet has not been exploited in previous works. We first show the benefits of `test-time adaptation' through simple fine-tuning of a network, then we greatly improve its efficiency by incorporating meta-learning. We obtain significant performance gains with only a single gradient update without any additional parameters. Finally, we show that our meta-learning framework can be easily employed to any video frame interpolation network and can consistently improve its performance on multiple benchmark datasets.