3D Video Loops From Asynchronous Input

Li Ma, Xiaoyu Li, Jing Liao, Pedro V. Sander

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

3 Citations (Scopus)

Abstract

Looping videos are short video clips that can be looped endlessly without visible seams or artifacts. They provide a very attractive way to capture the dynamism of natural scenes. Existing methods have been mostly limited to 2D representations. In this paper, we take a step forward and propose a practical solution that enables an immersive experience on dynamic 3D looping scenes. The key challenge is to consider the per-view looping conditions from asynchronous input while maintaining view consistency for the 3D representation. We propose a novel sparse 3D video representation, namely Multi-Tile Video (MTV), which not only provides a view-consistent prior, but also greatly reduces memory usage, making the optimization of a 4D volume tractable. Then, we introduce a two-stage pipeline to construct the 3D looping MTV from completely asynchronous multi-view videos with no time overlap. A novel looping loss based on video temporal retargeting algorithms is adopted during the optimization to loop the 3D scene. Experiments of our framework have shown promise in successfully generating and rendering photorealistic 3D looping videos in real time even on mobile devices. The code, dataset, and live demos are available in https://limacv.github.io/VideoLoop3D-web/. © 2023 IEEE.
Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition
PublisherIEEE
Pages310-320
ISBN (Electronic)9798350301298
ISBN (Print)979-8-3503-0130-4
DOIs
Publication statusPublished - 2023
Event2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023) - Vancouver Convention Center, Vancouver, Canada
Duration: 18 Jun 202322 Jun 2023
https://cvpr2023.thecvf.com/Conferences/2023
https://openaccess.thecvf.com/menu
https://ieeexplore.ieee.org/xpl/conhome/1000147/all-proceedings

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919
ISSN (Electronic)2575-7075

Conference

Conference2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023)
Abbreviated titleCVPR2023
Country/TerritoryCanada
CityVancouver
Period18/06/2322/06/23
Internet address

Bibliographical note

Research Unit(s) information for this publication is provided by the author(s) concerned.

Funding

The authors from HKUST were partially supported by the Hong Kong Research Grants Council (RGC). The author from CityU was partially supported by an ECS grant from the RGC (Project No. CityU 21209119).

Research Keywords

  • 3D from multi-view and sensors

Fingerprint

Dive into the research topics of '3D Video Loops From Asynchronous Input'. Together they form a unique fingerprint.

Cite this