Framer: Interactive Frame Interpolation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Wen, Wang, Qiuyu, Zheng, Kecheng, Ouyang, Hao, Chen, Zhekai, Gong, Biao, Chen, Hao, Shen, Yujun, Shen, Chunhua
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910683269955584
author Wang, Wen
Wang, Qiuyu
Zheng, Kecheng
Ouyang, Hao
Chen, Zhekai
Gong, Biao
Chen, Hao
Shen, Yujun
Shen, Chunhua
author_facet Wang, Wen
Wang, Qiuyu
Zheng, Kecheng
Ouyang, Hao
Chen, Zhekai
Gong, Biao
Chen, Hao
Shen, Yujun
Shen, Chunhua
contents We propose Framer for interactive frame interpolation, which targets producing smoothly transitioning frames between two images as per user creativity. Concretely, besides taking the start and end frames as inputs, our approach supports customizing the transition process by tailoring the trajectory of some selected keypoints. Such a design enjoys two clear benefits. First, incorporating human interaction mitigates the issue arising from numerous possibilities of transforming one image to another, and in turn enables finer control of local motions. Second, as the most basic form of interaction, keypoints help establish the correspondence across frames, enhancing the model to handle challenging cases (e.g., objects on the start and end frames are of different shapes and styles). It is noteworthy that our system also offers an "autopilot" mode, where we introduce a module to estimate the keypoints and refine the trajectory automatically, to simplify the usage in practice. Extensive experimental results demonstrate the appealing performance of Framer on various applications, such as image morphing, time-lapse video generation, cartoon interpolation, etc. The code, the model, and the interface will be released to facilitate further research.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18978
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Framer: Interactive Frame Interpolation
Wang, Wen
Wang, Qiuyu
Zheng, Kecheng
Ouyang, Hao
Chen, Zhekai
Gong, Biao
Chen, Hao
Shen, Yujun
Shen, Chunhua
Computer Vision and Pattern Recognition
We propose Framer for interactive frame interpolation, which targets producing smoothly transitioning frames between two images as per user creativity. Concretely, besides taking the start and end frames as inputs, our approach supports customizing the transition process by tailoring the trajectory of some selected keypoints. Such a design enjoys two clear benefits. First, incorporating human interaction mitigates the issue arising from numerous possibilities of transforming one image to another, and in turn enables finer control of local motions. Second, as the most basic form of interaction, keypoints help establish the correspondence across frames, enhancing the model to handle challenging cases (e.g., objects on the start and end frames are of different shapes and styles). It is noteworthy that our system also offers an "autopilot" mode, where we introduce a module to estimate the keypoints and refine the trajectory automatically, to simplify the usage in practice. Extensive experimental results demonstrate the appealing performance of Framer on various applications, such as image morphing, time-lapse video generation, cartoon interpolation, etc. The code, the model, and the interface will be released to facilitate further research.
title Framer: Interactive Frame Interpolation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.18978