StegaNeRF: Embedding Invisible Information within Neural Radiance Fields
This addresses the need for steganographic information embedding in emerging NeRF formats for content creators and distributors, though it is an initial exploration and thus incremental in this novel domain.
The authors tackled the problem of embedding ownership or copyright information in Neural Radiance Fields (NeRF) renderings, which lacked standard approaches, by developing StegaNeRF, a method that enables accurate hidden information extraction from rendered images while preserving visual quality.
Recent advances in neural rendering imply a future of widespread visual data distributions through sharing NeRF model weights. However, while common visual data (images and videos) have standard approaches to embed ownership or copyright information explicitly or subtly, the problem remains unexplored for the emerging NeRF format. We present StegaNeRF, a method for steganographic information embedding in NeRF renderings. We design an optimization framework allowing accurate hidden information extractions from images rendered by NeRF, while preserving its original visual quality. We perform experimental evaluations of our method under several potential deployment scenarios, and we further discuss the insights discovered through our analysis. StegaNeRF signifies an initial exploration into the novel problem of instilling customizable, imperceptible, and recoverable information to NeRF renderings, with minimal impact to rendered images. Project page: https://xggnet.github.io/StegaNeRF/.