Video super-resolution using motion compensation and classification-aided fusion

Simonyan, Karen; Grishin, S. G.; Vatolin, Dmitriy; Popov, D. I.

doi:10.1145/1921264.1921294

Search citation statements

Order By: Relevance

Paper Sections

Select...

Optical-flow and Consistency Maps1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2021

2023

Publication Types

Select...

Other2

Relationship

Self Cite0

Independent2

Authors

Journals

Cited by 2 publications

(1 citation statement)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, a block-based motion-estimation algorithm from [27] processes pairs of subsequent frames from the input video {I i } N i=1 in forward and reverse order to yield forward and backward motion vectors in the form of optical-flow maps: the resulting maps as…”

Section: Optical-flow and Consistency Mapsmentioning

confidence: 99%

Temporally Coherent Person Matting Trained on Fake-Motion Dataset

Molodetskikh¹,

Ерофеев²,

Moskalenko³

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose a novel neural-network-based method to perform matting of videos depicting people that does not require additional user input such as trimaps. Our architecture achieves temporal stability of the resulting alpha mattes by using motion-estimation-based smoothing of image-segmentation algorithm outputs, combined with convolutional-LSTM modules on U-Net skip connections.We also propose a fake-motion algorithm that generates training clips for the videomatting network given photos with ground-truth alpha mattes and background videos. We apply random motion to photos and their mattes to simulate movement one would find in real videos and composite the result with the background clips. It lets us train a deep neural network operating on videos in an absence of a large annotated video dataset and provides ground-truth training-clip foreground optical flow for use in loss functions.

show abstract

Section: Optical-flow and Consistency Mapsmentioning

confidence: 99%