NeRFCom: Feature Transform Coding Meets Neural Radiance Field for Free-View 3D Scene Semantic Transmission
This work addresses efficient 3D scene communication for applications like virtual reality, but it appears incremental as it builds on existing NeRF-based methods with specific coding improvements.
The paper tackles the problem of efficient 3D scene transmission by introducing NeRFCom, a system that uses nonlinear transforms and learned probabilistic models for joint source-channel coding, achieving robust free-view transmission under adverse conditions.
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.