Clone with HTTP

 git clone https://www.modelscope.cn/Damo_XR_Lab/cv_rife_video-frame-interpolation.git

视频插帧介绍

任务

给定一段低帧率视频，模型会返回更流畅的高帧率视频（默认为输入帧率两倍）。

模型描述

本模型基于Real-Time Intermediate Flow Estimation for Video Frame Interpolation， 适用于各类低帧率视频增强，用于提升视频的流畅度，消除卡顿现象。

技术细节请见： [Paper] | [Project Page]

代码示例

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
from modelscope.outputs import OutputKeys

video = 'https://modelscope.oss-cn-beijing.aliyuncs.com/test/videos/video_frame_interpolation_test.mp4'
video_frame_interpolation_pipeline = pipeline(Tasks.video_frame_interpolation, 'Damo_XR_Lab/cv_rife_video-frame-interpolation')
result = video_frame_interpolation_pipeline(video)[OutputKeys.OUTPUT_VIDEO]
print('pipeline: the output video path is {}'.format(result))

相关论文以及引用信息

该模型借鉴了以下论文的思路或代码，感谢作者的贡献！

@inproceedings{huang2022rife,
  title={Real-Time Intermediate Flow Estimation for Video Frame Interpolation},
  author={Huang, Zhewei and Zhang, Tianyuan and Heng, Wen and Shi, Boxin and Zhou, Shuchang},
  booktitle={Proceedings of the European Conference on Computer Vision (ECCV)},
  year={2022}
}