NeRFCom: Feature Transform Coding Meets Neural Radiance Field for Free-View 3D Scene Semantic Transmission

TL;DR

NeRFCom is a novel end-to-end system that combines feature transform coding with neural radiance fields to efficiently transmit 3D scenes for free-view rendering, adapting to channel conditions.

Contribution

It introduces a nonlinear transform and learned probabilistic models for flexible joint source-channel coding in 3D scene transmission.

Findings

Achieves efficient free-view 3D scene transmission

Maintains robustness under adverse channel conditions

Enables adaptive bandwidth allocation

Abstract

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.