Noise-NeRF: Hide Information in Neural Radiance Fields using Trainable Noise
This addresses steganography in 3D reconstruction for applications requiring secure data hiding, but it is incremental as it builds on existing NeRF methods.
The paper tackles the problem of information confidentiality and security in Neural Radiance Fields (NeRF) for steganography, proposing Noise-NeRF to improve steganography quality and efficiency, achieving state-of-the-art performances in both steganography and rendering quality.
Neural Radiance Field (NeRF) has been proposed as an innovative advancement in 3D reconstruction techniques. However, little research has been conducted on the issues of information confidentiality and security to NeRF, such as steganography. Existing NeRF steganography solutions have shortcomings in low steganography quality, model weight damage, and limited amount of steganographic information. This paper proposes Noise-NeRF, a novel NeRF steganography method employing Adaptive Pixel Selection strategy and Pixel Perturbation strategy to improve the quality and efficiency of steganography via trainable noise. Extensive experiments validate the state-of-the-art performances of Noise-NeRF on both steganography quality and rendering quality, as well as effectiveness in super-resolution image steganography.