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.
View on arXiv@article{yue2025_2502.19873,
title={ NeRFCom: Feature Transform Coding Meets Neural Radiance Field for Free-View 3D Scene Semantic Transmission },
author={ Weijie Yue and Zhongwei Si and Bolin Wu and Sixian Wang and Xiaoqi Qin and Kai Niu and Jincheng Dai and Ping Zhang },
journal={arXiv preprint arXiv:2502.19873},
year={ 2025 }
}