Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhong, Houqiang, Zheng, Zihan, Hu, Qiang, Tian, Yuan, Cao, Ning, Xu, Lan, Zhang, Xiaoyun, Cheng, Zhengxue, Song, Li, Zhang, Wenjun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2509.17506
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915506523471872
author Zhong, Houqiang
Zheng, Zihan
Hu, Qiang
Tian, Yuan
Cao, Ning
Xu, Lan
Zhang, Xiaoyun
Cheng, Zhengxue
Song, Li
Zhang, Wenjun
author_facet Zhong, Houqiang
Zheng, Zihan
Hu, Qiang
Tian, Yuan
Cao, Ning
Xu, Lan
Zhang, Xiaoyun
Cheng, Zhengxue
Song, Li
Zhang, Wenjun
contents Volumetric video has emerged as a key medium for immersive telepresence and augmented/virtual reality, enabling six-degrees-of-freedom (6DoF) navigation and realistic spatial interactions. However, delivering high-quality dynamic volumetric content at scale remains challenging due to massive data volume, complex motion, and limited editability of existing representations. In this paper, we present 4D-MoDe, a motion-decoupled 4D Gaussian compression framework designed for scalable and editable volumetric video streaming. Our method introduces a layered representation that explicitly separates static backgrounds from dynamic foregrounds using a lookahead-based motion decomposition strategy, significantly reducing temporal redundancy and enabling selective background/foreground streaming. To capture continuous motion trajectories, we employ a multi-resolution motion estimation grid and a lightweight shared MLP, complemented by a dynamic Gaussian compensation mechanism to model emergent content. An adaptive grouping scheme dynamically inserts background keyframes to balance temporal consistency and compression efficiency. Furthermore, an entropy-aware training pipeline jointly optimizes the motion fields and Gaussian parameters under a rate-distortion (RD) objective, while employing range-based and KD-tree compression to minimize storage overhead. Extensive experiments on multiple datasets demonstrate that 4D-MoDe consistently achieves competitive reconstruction quality with an order of magnitude lower storage cost (e.g., as low as \textbf{11.4} KB/frame) compared to state-of-the-art methods, while supporting practical applications such as background replacement and foreground-only streaming.
format Preprint
id arxiv_https___arxiv_org_abs_2509_17506
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle 4D-MoDe: Towards Editable and Scalable Volumetric Streaming via Motion-Decoupled 4D Gaussian Compression
Zhong, Houqiang
Zheng, Zihan
Hu, Qiang
Tian, Yuan
Cao, Ning
Xu, Lan
Zhang, Xiaoyun
Cheng, Zhengxue
Song, Li
Zhang, Wenjun
Computer Vision and Pattern Recognition
Volumetric video has emerged as a key medium for immersive telepresence and augmented/virtual reality, enabling six-degrees-of-freedom (6DoF) navigation and realistic spatial interactions. However, delivering high-quality dynamic volumetric content at scale remains challenging due to massive data volume, complex motion, and limited editability of existing representations. In this paper, we present 4D-MoDe, a motion-decoupled 4D Gaussian compression framework designed for scalable and editable volumetric video streaming. Our method introduces a layered representation that explicitly separates static backgrounds from dynamic foregrounds using a lookahead-based motion decomposition strategy, significantly reducing temporal redundancy and enabling selective background/foreground streaming. To capture continuous motion trajectories, we employ a multi-resolution motion estimation grid and a lightweight shared MLP, complemented by a dynamic Gaussian compensation mechanism to model emergent content. An adaptive grouping scheme dynamically inserts background keyframes to balance temporal consistency and compression efficiency. Furthermore, an entropy-aware training pipeline jointly optimizes the motion fields and Gaussian parameters under a rate-distortion (RD) objective, while employing range-based and KD-tree compression to minimize storage overhead. Extensive experiments on multiple datasets demonstrate that 4D-MoDe consistently achieves competitive reconstruction quality with an order of magnitude lower storage cost (e.g., as low as \textbf{11.4} KB/frame) compared to state-of-the-art methods, while supporting practical applications such as background replacement and foreground-only streaming.
title 4D-MoDe: Towards Editable and Scalable Volumetric Streaming via Motion-Decoupled 4D Gaussian Compression
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.17506