arrow
返回

Motion-Aware Video Frame Interpolation

delete2024-10-01
delete0
delete
OA
AI
P
Pengfei Han
F
Fuhua Zhang
B
Bin Zhao *
X
Xuelong Li
DOI:10.1016/j.neunet.2024.106433delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Video frame interpolation methodologies endeavor to create novel frames betwixt extant ones, with the intent of augmenting the video's frame frequency. However, current methods are prone to image blurring and spurious artifacts in challenging scenarios involving occlusions and discontinuous motion. Moreover, they typically rely on optical flow estimation, which adds complexity to modeling and computational costs. To address these issues, we introduce a Motion -Aware Video Frame Interpolation (MA-VFI) network, which directly estimates intermediate optical flow from consecutive frames by introducing a novel hierarchical pyramid module. It not only extracts global semantic relationships and spatial details from input frames with different receptive fields, enabling the model to capture intricate motion patterns, but also effectively reduces the required computational cost and complexity. Subsequently, a cross -scale motion structure is presented to estimate and refine intermediate flow maps by the extracted features. This approach facilitates the interplay between input frame features and flow maps during the frame interpolation process and markedly heightens the precision of the intervening flow delineations. Finally, a discerningly fashioned loss centered around an intermediate flow is meticulously contrived, serving as a deft rudder to skillfully guide the prognostication of said intermediate flow, thereby substantially refining the precision of the intervening flow mappings. Experiments illustrate that MA-VFI surpasses several representative VFI methods across various datasets, and can enhance efficiency while maintaining commendable efficacy.
Keyword:
Intermediate flow estimation
Flow-directed loss
Video frame interpolation
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neural Networks 封面图
Neural Networks
IF:
6.3
论文数:
8.2K
被引数:
3.0W

机构

N
Northwestern Polytechnical University
学者数:
4.6W
论文数: 3.7W
被引数: 5.3W
H
hunan university
学者数:
4.5W
论文数: 3.3W
被引数: 70
引用论文

引用论文

Video Frame Interpolation via Generalized Deformable Convolution
err2022-01-01
err41
errOAAI
errShi, Zhihao; Liu, Xiaohong; Shi, Kangdi; Dai, Linhui; Chen, Jun
err分享
err收藏
Angle-dispersive powder-diffraction techniques for crystal structure refinement at high pressure
err1992-01-01
err0
PREAI
errR. J. Nelmes; P. D. Hatton; M. I. McMahon; R. O. Piltz; J. Crain; R. J. Cernik; G. Bushnell-Wye
err分享
err收藏
PHOTODYNAMIC THERAPY USING VERTEPORFIN FOR A DIFFUSE CHOROIDAL HEMANGIOMA IN STURGE–WEBER SYNDROME
err2004-02-01
err0
PREAI
errHARSHIVINDERJIT S. BAINS; ANTHONY C. CIRINO; BENJAMIN H. TICHO; LEE M. JAMPOL
err分享
err收藏
Multi-Frame Pyramid Refinement Network for Video Frame Interpolation
err2019-01-01
err13
errOAAI
errZhang, Haoxian; Wang, Ronggang; Zhao, Yang
err分享
err收藏
学者 查看更多内容