# Enhanced Deep Animation Video Interpolation

arXiv: https://arxiv.org/abs/2206.12657 · HTML: https://mlsanity.com/paper/2206.12657/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 20 references that are in the map.
- First posted on arXiv 25 Jun 2022.

## Builds on (most cited first, 14 of 14)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [Softmax Splatting for Video Frame Interpolation](https://mlsanity.com/paper/2003.05534/) (2020)
- [Depth-Aware Video Frame Interpolation](https://mlsanity.com/paper/1904.00830/) (2019)
- [AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation](https://mlsanity.com/paper/1907.10244/) (2019)
- [BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation](https://mlsanity.com/paper/2007.12622/) (2020)
- [AutoFlow: Learning a Better Training Set for Optical Flow](https://mlsanity.com/paper/2104.14544/) (2021)
- [Deep Animation Video Interpolation in the Wild](https://mlsanity.com/paper/2104.02495/) (2021)
- [Blurry Video Frame Interpolation](https://mlsanity.com/paper/2002.12259/) (2020)
- [Revisiting Adaptive Convolutions for Video Frame Interpolation](https://mlsanity.com/paper/2011.01280/) (2020)
- [FaceShop: Deep Sketch-based Face Image Editing](https://mlsanity.com/paper/1804.08972/) (2018)
- [Mastering Sketching: Adversarial Augmentation for Structured Prediction](https://mlsanity.com/paper/1703.08966/) (2017)

## Built on by (most cited first, 8 of 8)

- [Generative AI for Cel-Animation: A Survey](https://mlsanity.com/paper/2501.06250/) (2025)
- [APISR: Anime Production Inspired Real-World Anime Super-Resolution](https://mlsanity.com/paper/2403.01598/) (2024)
- [Video Frame Interpolation with Densely Queried Bilateral Correlation](https://mlsanity.com/paper/2304.13596/) (2023)
- [ToonComposer: Streamlining Cartoon Production with Generative Post-Keyframing](https://mlsanity.com/paper/2508.10881/) (2025)
- [H2-Stereo: High-Speed, High-Resolution Stereoscopic Video System](https://mlsanity.com/paper/2208.02436/) (2022)
- [InstanceAnimator: Multi-Instance Sketch Video Colorization](https://mlsanity.com/paper/2603.25357/) (2026)
- [MagicAnime: A Hierarchically Annotated, Multimodal and Multitasking Dataset with Benchmarks for Cartoon Animation Generation](https://mlsanity.com/paper/2507.20368/) (2025)
- [Uni-Animator: Towards Unified Visual Colorization](https://mlsanity.com/paper/2602.23191/) (2026)

## Abstract (arXiv)

Existing learning-based frame interpolation algorithms extract consecutive frames from high-speed natural videos to train the model. Compared to natural videos, cartoon videos are usually in a low frame rate. Besides, the motion between consecutive cartoon frames is typically nonlinear, which breaks the linear motion assumption of interpolation algorithms. Thus, it is unsuitable for generating a training set directly from cartoon videos. For better adapting frame interpolation algorithms from nature video to animation video, we present AutoFI, a simple and effective method to automatically render training data for deep animation video interpolation. AutoFI takes a layered architecture to render synthetic data, which ensures the assumption of linear motion. Experimental results show that AutoFI performs favorably in training both DAIN and ANIN. However, most frame interpolation algorithms will still fail in error-prone areas, such as fast motion or large occlusion. Besides AutoFI, we also propose a plug-and-play sketch-based post-processing module, named SktFI, to refine the final results using user-provided sketches manually. With AutoFI and SktFI, the interpolated animation frames show high perceptual quality.