Salvato in:
Dettagli Bibliografici
Autori principali: Yue, Weijie, Si, Zhongwei, Wu, Bolin, Wang, Sixian, Qin, Xiaoqi, Niu, Kai, Dai, Jincheng, Zhang, Ping
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2502.19873
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866929734129025024
author Yue, Weijie
Si, Zhongwei
Wu, Bolin
Wang, Sixian
Qin, Xiaoqi
Niu, Kai
Dai, Jincheng
Zhang, Ping
author_facet Yue, Weijie
Si, Zhongwei
Wu, Bolin
Wang, Sixian
Qin, Xiaoqi
Niu, Kai
Dai, Jincheng
Zhang, Ping
contents We introduce NeRFCom, a novel communication system designed for end-to-end 3D scene transmission. Compared to traditional systems relying on handcrafted NeRF semantic feature decomposition for compression and well-adaptive channel coding for transmission error correction, our NeRFCom employs a nonlinear transform and learned probabilistic models, enabling flexible variable-rate joint source-channel coding and efficient bandwidth allocation aligned with the NeRF semantic feature's different contribution to the 3D scene synthesis fidelity. Experimental results demonstrate that NeRFCom achieves free-view 3D scene efficient transmission while maintaining robustness under adverse channel conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2502_19873
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle NeRFCom: Feature Transform Coding Meets Neural Radiance Field for Free-View 3D Scene Semantic Transmission
Yue, Weijie
Si, Zhongwei
Wu, Bolin
Wang, Sixian
Qin, Xiaoqi
Niu, Kai
Dai, Jincheng
Zhang, Ping
Signal Processing
Machine Learning
We introduce NeRFCom, a novel communication system designed for end-to-end 3D scene transmission. Compared to traditional systems relying on handcrafted NeRF semantic feature decomposition for compression and well-adaptive channel coding for transmission error correction, our NeRFCom employs a nonlinear transform and learned probabilistic models, enabling flexible variable-rate joint source-channel coding and efficient bandwidth allocation aligned with the NeRF semantic feature's different contribution to the 3D scene synthesis fidelity. Experimental results demonstrate that NeRFCom achieves free-view 3D scene efficient transmission while maintaining robustness under adverse channel conditions.
title NeRFCom: Feature Transform Coding Meets Neural Radiance Field for Free-View 3D Scene Semantic Transmission
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2502.19873