BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Seo, Wonyong, Oh, Jihyong, Kim, Munchurl
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909548810338304
author Seo, Wonyong
Oh, Jihyong
Kim, Munchurl
author_facet Seo, Wonyong
Oh, Jihyong
Kim, Munchurl
contents Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred interpolated frames. In this paper, we propose (i) a novel motion description map, Bidirectional Motion field (BiM), to effectively describe non-uniform motions; (ii) a BiM-guided Flow Net (BiMFN) with Content-Aware Upsampling Network (CAUN) for precise optical flow estimation; and (iii) Knowledge Distillation for VFI-centric Flow supervision (KDVCF) to supervise the motion estimation of VFI model with VFI-centric teacher flows. The proposed VFI is called a Bidirectional Motion field-guided VFI (BiM-VFI) model. Extensive experiments show that our BiM-VFI model significantly surpasses the recent state-of-the-art VFI methods by 26% and 45% improvements in LPIPS and STLPIPS respectively, yielding interpolated frames with much fewer blurs at arbitrary time instances.
format Preprint
id arxiv_https___arxiv_org_abs_2412_11365
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions
Seo, Wonyong
Oh, Jihyong
Kim, Munchurl
Computer Vision and Pattern Recognition
Existing Video Frame interpolation (VFI) models tend to suffer from time-to-location ambiguity when trained with video of non-uniform motions, such as accelerating, decelerating, and changing directions, which often yield blurred interpolated frames. In this paper, we propose (i) a novel motion description map, Bidirectional Motion field (BiM), to effectively describe non-uniform motions; (ii) a BiM-guided Flow Net (BiMFN) with Content-Aware Upsampling Network (CAUN) for precise optical flow estimation; and (iii) Knowledge Distillation for VFI-centric Flow supervision (KDVCF) to supervise the motion estimation of VFI model with VFI-centric teacher flows. The proposed VFI is called a Bidirectional Motion field-guided VFI (BiM-VFI) model. Extensive experiments show that our BiM-VFI model significantly surpasses the recent state-of-the-art VFI methods by 26% and 45% improvements in LPIPS and STLPIPS respectively, yielding interpolated frames with much fewer blurs at arbitrary time instances.
title BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.11365