Video Frame Interpolation Based on Symmetric and Asymmetric Motions

Whan Choi, Yeong Jun Koh, Chang Su Kim

Research output: Contribution to journalArticlepeer-review


Video frame interpolation is the task to synthesize intermediate frames between consecutive frames to increase the frame rate. Recently, various deep-learning techniques have been proposed to interpolate intermediate frames more reliably. However, many existing methods use either symmetric (linear) or asymmetric (non-linear) schemes only to estimate motions for the warping process, resulting in unreliable interpolation results. In this paper, we propose a novel video frame interpolation network based on both symmetric and asymmetric motion-based warping modules, which can deal with linear and non-linear motions, as well as occlusions, effectively. The symmetric warping module estimates symmetric motions to generate intermediate frames, while the asymmetric one predicts asymmetric motions to address non-linear motions and occlusion problems. We combine symmetric and asymmetric warping results to reconstruct intermediate frames more reliably. We also develop the frame synthesis network to refine the combined warping results. Experimental results demonstrate that the proposed network outperforms state-of-the-art video interpolation algorithms and that the two types of warping modules work effectively in a complementary manner on various benchmark datasets.

Original languageEnglish
Pages (from-to)22394-22403
Number of pages10
JournalIEEE Access
Publication statusPublished - 2023

Bibliographical note

Funding Information:
This work was supported in part by the National Research Foundation of Korea (NRF) grant funded by the Korea Government (MSIT) under Grant NRF-2021R1A4A1031864 and Grant NRF-2022R1A2B5B03002310, in part by the Basic Science Research Program through the NRF funded by the Ministry of Education under Grant NRF-2022R1I1A3069113, and in part by Samsung Electronics Company Ltd. under Grant IO201214-08156-01.

Publisher Copyright:
© 2013 IEEE.


  • Video frame interpolation
  • asymmetric motion
  • convolutional neural network
  • deformable convolution
  • frame synthesis
  • kernel-based approach
  • motion estimation
  • symmetric motion

ASJC Scopus subject areas

  • General Computer Science
  • General Materials Science
  • General Engineering
  • Electrical and Electronic Engineering


Dive into the research topics of 'Video Frame Interpolation Based on Symmetric and Asymmetric Motions'. Together they form a unique fingerprint.

Cite this