NeuVV: Neural Volumetric Videos with Immersive Rendering and Editing

Zhang, Jiakai; Wang, Liao; Liu, Xinhang; Zhao, Fuqiang; Li, Minzhang; Dai, Haizhao; Zhang, Boyuan; Yang, Wei; Xu, Li; Yu, Jing

doi:10.48550/arxiv.2202.06088

Search citation statements

Order By: Relevance

Paper Sections

Select...

Related Work1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, reconstructing an accurate, temporally consistent mesh is still an open problem, being particularly challenging for complex in-the-wild scenes [28]. A volumetric representation is another option to express the 3D world by storing scene parameters in a dense 3D grid [11,27,49,54]. One benefit is that it trivially supports differentiable rendering, which greatly improves the reconstruction quality.…”

Section: Related Workmentioning

confidence: 99%

3D Video Loops from Asynchronous Input

Li¹,

Li²,

Liao³

et al. 2023

Preprint

View full text Add to dashboard Cite

Kong(a) Reconstructed 3D Video Representation (b) View and Time Control (c) Real Time Demo Figure 1. Given a set of asynchronous multi-view videos, we propose a pipeline to construct a novel 3D looping video representation (a), which consists of a static texture atlas, a dynamic texture atlas, and multiple tiles as the geometry proxy. The 3D video loops allow both view and time control (b), and can be rendered in real time even on mobile devices (c). We strongly recommend readers refer to the supplementary material for video results.

show abstract