# Video Frame Interpolation with Flow Transformer

arXiv: https://arxiv.org/abs/2307.16144 · HTML: https://mlsanity.com/paper/2307.16144/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 30 Jul 2023.

## Builds on (most cited first, 21 of 21)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [EDVR: Video Restoration with Enhanced Deformable Convolutional Networks](https://mlsanity.com/paper/1905.02716/) (2019)
- [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)
- [Video Frame Interpolation via Adaptive Separable Convolution](https://mlsanity.com/paper/1708.01692/) (2017)
- [Video Frame Synthesis using Deep Voxel Flow](https://mlsanity.com/paper/1702.02463/) (2017)
- [Video Frame Interpolation via Adaptive Convolution](https://mlsanity.com/paper/1703.07514/) (2017)
- [Context-aware Synthesis for Video Frame Interpolation](https://mlsanity.com/paper/1803.10967/) (2018)
- [Quadratic video interpolation](https://mlsanity.com/paper/1911.00627/) (2019)
- [AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation](https://mlsanity.com/paper/1907.10244/) (2019)
- [Video Frame Interpolation Transformer](https://mlsanity.com/paper/2111.13817/) (2021)
- [MEMC-Net: Motion Estimation and Motion Compensation Driven Neural Network for Video Interpolation and Enhancement](https://mlsanity.com/paper/1810.08768/) (2018)
- [Deep Slow Motion Video Reconstruction with Hybrid Imaging System](https://mlsanity.com/paper/2002.12106/) (2020)
- [Video Frame Interpolation Based on Deformable Kernel Region](https://mlsanity.com/paper/2204.11396/) (2022)

## Built on by (most cited first, 2 of 2)

- [MoSt-DSA: Modeling Motion and Structural Interactions for Direct Multi-Frame Interpolation in DSA Images](https://mlsanity.com/paper/2407.07078/) (2024)
- [GaraMoSt: Parallel Multi-Granularity Motion and Structural Modeling for Efficient Multi-Frame Interpolation in DSA Images](https://mlsanity.com/paper/2412.14118/) (2024)

## Abstract (arXiv)

Video frame interpolation has been actively studied with the development of convolutional neural networks. However, due to the intrinsic limitations of kernel weight sharing in convolution, the interpolated frame generated by it may lose details. In contrast, the attention mechanism in Transformer can better distinguish the contribution of each pixel, and it can also capture long-range pixel dependencies, which provides great potential for video interpolation. Nevertheless, the original Transformer is commonly used for 2D images; how to develop a Transformer-based framework with consideration of temporal self-attention for video frame interpolation remains an open issue. In this paper, we propose Video Frame Interpolation Flow Transformer to incorporate motion dynamics from optical flows into the self-attention mechanism. Specifically, we design a Flow Transformer Block that calculates the temporal self-attention in a matched local area with the guidance of flow, making our framework suitable for interpolating frames with large motion while maintaining reasonably low complexity. In addition, we construct a multi-scale architecture to account for multi-scale motion, further improving the overall performance. Extensive experiments on three benchmarks demonstrate that the proposed method can generate interpolated frames with better visual quality than state-of-the-art methods.