WhisperSplat: Lossless Steganography in 3D Gaussian Splatting

We present WhisperSplat, the first lossless steganography method for 3D Gaussian Splatting (3DGS) models that hides a full‐resolution 2D image in a single view without any degradation of the model's rendering quality elsewhere. Prior work embeds data by retraining or modifying model weights, altering novel‐view synthesis fidelity and limiting capacity. Instead, we learn a small, view‐specific noise key applied to each Gaussian's spherical‐harmonic (SH) features while keeping all other views remain indistinguishable from the original renders. We further propose a Gradual Pixel Perturbation (GPP) strategy with a cosine-decay schedule, bootstrapping fast divergence from the clean render before transitioning to a combined reconstruction and SSIM loss. Unlike prior works that are highly dependent on accurate and large pretrained decoders, our method is able to recover the hidden image through rendering with noise key, and an optional lightweight refiner to enhance recovery image quality. Across nine standard 3DGS data scenes, WhisperSplat demonstrates superior hidden image recovery quality without sacrifice in clean 3DGS model performance, when compared to prior work such as GS-Hider and KeySS.

3D reconstruction models are increasingly used to create realistic digital scenes for virtual reality, robotics, graphics, and online content, but protecting these assets after they are shared remains challenging. Existing methods for hiding information in 3D models often change the model itself or reduce the quality of the rendered scene. We introduce WhisperSplat, a method that hides a full resolution image inside a 3D scene using a secret key, allowing the image to be recovered only from a selected viewpoint while ordinary views remain unchanged. This allows ownership verification, private information embedding, and secure use of 3D digital assets without compromising visual quality.