Saved in:
Bibliographic Details
Main Authors: Bai, Xue, Haque, Tasmiah, Mohan, Sumit, Cai, Yuliang, Jeong, Byungheon, Halasz, Adam, Das, Srinjoy
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.11337
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913269302689792
author Bai, Xue
Haque, Tasmiah
Mohan, Sumit
Cai, Yuliang
Jeong, Byungheon
Halasz, Adam
Das, Srinjoy
author_facet Bai, Xue
Haque, Tasmiah
Mohan, Sumit
Cai, Yuliang
Jeong, Byungheon
Halasz, Adam
Das, Srinjoy
contents We propose a deep learning based novel prediction framework for enhanced bandwidth reduction in motion transfer enabled video applications such as video conferencing, virtual reality gaming and privacy preservation for patient health monitoring. To model complex motion, we use the First Order Motion Model (FOMM) that represents dynamic objects using learned keypoints along with their local affine transformations. Keypoints are extracted by a self-supervised keypoint detector and organized in a time series corresponding to the video frames. Prediction of keypoints, to enable transmission using lower frames per second on the source device, is performed using a Variational Recurrent Neural Network (VRNN). The predicted keypoints are then synthesized to video frames using an optical flow estimator and a generator network. This efficacy of leveraging keypoint based representations in conjunction with VRNN based prediction for both video animation and reconstruction is demonstrated on three diverse datasets. For real-time applications, our results show the effectiveness of our proposed architecture by enabling up to 2x additional bandwidth reduction over existing keypoint based video motion transfer frameworks without significantly compromising video quality.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11337
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Bandwidth Efficiency for Video Motion Transfer Applications using Deep Learning Based Keypoint Prediction
Bai, Xue
Haque, Tasmiah
Mohan, Sumit
Cai, Yuliang
Jeong, Byungheon
Halasz, Adam
Das, Srinjoy
Computer Vision and Pattern Recognition
Artificial Intelligence
We propose a deep learning based novel prediction framework for enhanced bandwidth reduction in motion transfer enabled video applications such as video conferencing, virtual reality gaming and privacy preservation for patient health monitoring. To model complex motion, we use the First Order Motion Model (FOMM) that represents dynamic objects using learned keypoints along with their local affine transformations. Keypoints are extracted by a self-supervised keypoint detector and organized in a time series corresponding to the video frames. Prediction of keypoints, to enable transmission using lower frames per second on the source device, is performed using a Variational Recurrent Neural Network (VRNN). The predicted keypoints are then synthesized to video frames using an optical flow estimator and a generator network. This efficacy of leveraging keypoint based representations in conjunction with VRNN based prediction for both video animation and reconstruction is demonstrated on three diverse datasets. For real-time applications, our results show the effectiveness of our proposed architecture by enabling up to 2x additional bandwidth reduction over existing keypoint based video motion transfer frameworks without significantly compromising video quality.
title Enhancing Bandwidth Efficiency for Video Motion Transfer Applications using Deep Learning Based Keypoint Prediction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2403.11337