# Unsupervised Video Interpolation Using Cycle Consistency

arXiv: https://arxiv.org/abs/1906.05928 · HTML: https://mlsanity.com/paper/1906.05928/

## Key facts

- Cited by 44 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2019.

## Built on by (most cited first, 30 of 44)

- [FILM: Frame Interpolation for Large Motion](https://mlsanity.com/paper/2202.04901/) (2022)
- [Asymmetric Bilateral Motion Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2108.06815/) (2021)
- [VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution](https://mlsanity.com/paper/2206.04647/) (2022)
- [CDFI: Compression-Driven Network Design for Frame Interpolation](https://mlsanity.com/paper/2103.10559/) (2021)
- [Generative Inbetweening: Adapting Image-to-Video Models for Keyframe Interpolation](https://mlsanity.com/paper/2408.15239/) (2024)
- [Many-to-many Splatting for Efficient Video Frame Interpolation](https://mlsanity.com/paper/2204.03513/) (2022)
- [TimeReplayer: Unlocking the Potential of Event Cameras for Video Interpolation](https://mlsanity.com/paper/2203.13859/) (2022)
- [ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation](https://mlsanity.com/paper/2111.15483/) (2021)
- [BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation](https://mlsanity.com/paper/2304.02225/) (2023)
- [ViBiDSampler: Enhancing Video Interpolation Using Bidirectional Diffusion Sampler](https://mlsanity.com/paper/2410.05651/) (2024)
- [Splatting-based Synthesis for Video Frame Interpolation](https://mlsanity.com/paper/2201.10075/) (2022)
- [View Generalization for Single Image Textured 3D Models](https://mlsanity.com/paper/2106.06533/) (2021)
- [Deep Video Prior for Video Consistency and Propagation](https://mlsanity.com/paper/2201.11632/) (2022)
- [Data-Efficient Unsupervised Interpolation Without Any Intermediate Frame for 4D Medical Images](https://mlsanity.com/paper/2404.01464/) (2024)
- [NTIRE 2021 Challenge on Video Super-Resolution](https://mlsanity.com/paper/2104.14852/) (2021)
- [Context-Aware Video Reconstruction for Rolling Shutter Cameras](https://mlsanity.com/paper/2205.12912/) (2022)
- [A Perceptual Quality Metric for Video Frame Interpolation](https://mlsanity.com/paper/2210.01879/) (2022)
- [NeuralPCI: Spatio-temporal Neural Field for 3D Point Cloud Multi-frame Non-linear Interpolation](https://mlsanity.com/paper/2303.15126/) (2023)
- [RIGID: Recurrent GAN Inversion and Editing of Real Face Videos](https://mlsanity.com/paper/2308.06097/) (2023)
- [SportsSloMo: A New Benchmark and Baselines for Human-centric Video Frame Interpolation](https://mlsanity.com/paper/2308.16876/) (2023)
- [AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation](https://mlsanity.com/paper/2506.01061/) (2025)
- [Two-Stage Self-Supervised Cycle-Consistency Network for Reconstruction of Thin-Slice MR Images](https://mlsanity.com/paper/2106.15395/) (2021)
- [Long-term Video Frame Interpolation via Feature Propagation](https://mlsanity.com/paper/2203.15427/) (2022)
- [Warp-Refine Propagation: Semi-Supervised Auto-labeling via Cycle-consistency](https://mlsanity.com/paper/2109.13432/) (2021)
- [BVI-VFI: A Video Quality Database for Video Frame Interpolation](https://mlsanity.com/paper/2210.00823/) (2022)
- [A unified model for continuous conditional video prediction](https://mlsanity.com/paper/2210.05810/) (2022)
- [Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video](https://mlsanity.com/paper/2210.03040/) (2022)
- [Zooming SlowMo: An Efficient One-Stage Framework for Space-Time Video Super-Resolution](https://mlsanity.com/paper/2104.07473/) (2021)
- [Frame Interpolation for Dynamic Scenes with Implicit Flow Encoding](https://mlsanity.com/paper/2209.13284/) (2022)
- [H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions](https://mlsanity.com/paper/2211.11309/) (2022)

## Abstract (arXiv)

Learning to synthesize high frame rate videos via interpolation requires large quantities of high frame rate training videos, which, however, are scarce, especially at high resolutions. Here, we propose unsupervised techniques to synthesize high frame rate videos directly from low frame rate videos using cycle consistency. For a triplet of consecutive frames, we optimize models to minimize the discrepancy between the center frame and its cycle reconstruction, obtained by interpolating back from interpolated intermediate frames. This simple unsupervised constraint alone achieves results comparable with supervision using the ground truth intermediate frames. We further introduce a pseudo supervised loss term that enforces the interpolated frames to be consistent with predictions of a pre-trained interpolation model. The pseudo supervised loss term, used together with cycle consistency, can effectively adapt a pre-trained model to a new target domain. With no additional data and in a completely unsupervised fashion, our techniques significantly improve pre-trained models on new target domains, increasing PSNR values from 32.84dB to 33.05dB on the Slowflow and from 31.82dB to 32.53dB on the Sintel evaluation datasets.