Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.06019 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914143840239616 |
|---|---|
| author | Srivastava, Priyansh Chatterjee, Romit Sen, Abir Behura, Aradhana Dash, Ratnakar |
| author_facet | Srivastava, Priyansh Chatterjee, Romit Sen, Abir Behura, Aradhana Dash, Ratnakar |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_06019 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MiVID: Multi-Strategic Self-Supervision for Video Frame Interpolation using Diffusion Model Srivastava, Priyansh Chatterjee, Romit Sen, Abir Behura, Aradhana Dash, Ratnakar Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | MiVID: Multi-Strategic Self-Supervision for Video Frame Interpolation using Diffusion Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.06019 |