# MiVID: Multi-Strategic Self-Supervision for Video Frame Interpolation using Diffusion Model

arXiv: https://arxiv.org/abs/2511.06019 · HTML: https://mlsanity.com/paper/2511.06019/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 8 Nov 2025.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [Masked Feature Prediction for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2112.09133/) (2021)
- [Future Frame Prediction for Anomaly Detection -- A New Baseline](https://mlsanity.com/paper/1712.09867/) (2017)
- [Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation](https://mlsanity.com/paper/1712.00080/) (2017)
- [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)
- [Real-Time Intermediate Flow Estimation for Video Frame Interpolation](https://mlsanity.com/paper/2011.06294/) (2020)
- [Context-aware Synthesis for Video Frame Interpolation](https://mlsanity.com/paper/1803.10967/) (2018)
- [FILM: Frame Interpolation for Large Motion](https://mlsanity.com/paper/2202.04901/) (2022)
- [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)
- [FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation](https://mlsanity.com/paper/2012.08512/) (2020)
- [Video Interpolation with Diffusion Models](https://mlsanity.com/paper/2404.01203/) (2024)
- [MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers](https://mlsanity.com/paper/2312.12468/) (2023)
- [Disentangled Motion Modeling for Video Frame Interpolation](https://mlsanity.com/paper/2406.17256/) (2024)
- [AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation](https://mlsanity.com/paper/2506.01061/) (2025)
- [TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation](https://mlsanity.com/paper/2507.04984/) (2025)
- [Self-supervised Learning of Event-guided Video Frame Interpolation for Rolling Shutter Frames](https://mlsanity.com/paper/2306.15507/) (2023)
- [EventDiff: A Unified and Efficient Diffusion Model Framework for Event-based Video Frame Interpolation](https://mlsanity.com/paper/2505.08235/) (2025)

## Abstract (arXiv)

Video Frame Interpolation (VFI) remains a cornerstone in video enhancement, enabling temporal upscaling for tasks like slow-motion rendering, frame rate conversion, and video restoration. While classical methods rely on optical flow and learning-based models assume access to dense ground-truth, both struggle with occlusions, domain shifts, and ambiguous motion. This article introduces MiVID, a lightweight, self-supervised, diffusion-based framework for video interpolation. Our model eliminates the need for explicit motion estimation by combining a 3D U-Net backbone with transformer-style temporal attention, trained under a hybrid masking regime that simulates occlusions and motion uncertainty. The use of cosine-based progressive masking and adaptive loss scheduling allows our network to learn robust spatiotemporal representations without any high-frame-rate supervision. Our framework is evaluated on UCF101-7 and DAVIS-7 datasets. MiVID is trained entirely on CPU using the datasets and 9-frame video segments, making it a low-resource yet highly effective pipeline. Despite these constraints, our model achieves optimal results at just 50 epochs, competitive with several supervised baselines.This work demonstrates the power of self-supervised diffusion priors for temporally coherent frame synthesis and provides a scalable path toward accessible and generalizable VFI systems.