Projects per year
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 language | English |
---|---|
Title of host publication | Proceedings - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition |
Publisher | IEEE |
Pages | 310-320 |
ISBN (Electronic) | 9798350301298 |
ISBN (Print) | 979-8-3503-0130-4 |
DOIs | |
Publication status | Published - 2023 |
Event | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023) - Vancouver Convention Center, Vancouver, Canada Duration: 18 Jun 2023 → 22 Jun 2023 https://cvpr2023.thecvf.com/Conferences/2023 https://openaccess.thecvf.com/menu https://ieeexplore.ieee.org/xpl/conhome/1000147/all-proceedings |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
ISSN (Print) | 1063-6919 |
ISSN (Electronic) | 2575-7075 |
Conference
Conference | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2023) |
---|---|
Abbreviated title | CVPR2023 |
Country/Territory | Canada |
City | Vancouver |
Period | 18/06/23 → 22/06/23 |
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.Projects
- 1 Finished
-
ECS: A Deep Learning Pipeline to Restore Images or Videos with Unknown and Mixed Defects
LIAO, J. (Principal Investigator / Project Coordinator)
1/08/19 → 24/07/23
Project: Research