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

TL;DR

MiVID introduces a self-supervised, diffusion-based video frame interpolation framework that eliminates explicit motion estimation, achieving competitive results with low resource requirements and broad applicability.

Contribution

It presents a novel self-supervised diffusion model for VFI that does not rely on dense ground-truth or explicit motion estimation, enhancing robustness and scalability.

Findings

Achieves competitive results on UCF101-7 and DAVIS-7 datasets.

Trained entirely on CPU in 50 epochs, demonstrating efficiency.

Outperforms several supervised baselines despite resource constraints.

Abstract

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.