IBRSteG: Learning a Generalizable Steganography Framework for 3D Gaussian Splatting
2026-06-29 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors developed IBRSteG, a method to hide secret 3D scenes within other 3D scenes using 3D Gaussian Splatting, a technique for representing 3D content. Unlike previous methods that need to be customized for each scene, their approach uses a network called GAS that learns to embed secret information in a general way across different scenes without extra tuning. This method converts 3D data into structured attributes compatible with 2D learning techniques, helping it work well on new, unseen scenes. Experiments show that their method hides secret scenes effectively while keeping good visual quality and security.
3D Gaussian SplattingSteganographyDeep LearningScene EmbeddingFeed-forward NetworkGeneralizationGaussian Attributes2D Learning ParadigmVisual QualityData Security
Authors
Fanye Kong, Hongyu Xia, Yu Zheng, Boyang Gong, Jie Zhou, Jiwen Lu
Abstract
Recent advances in deep learning have notably improved steganographic message hiding. However, designing a generalizable steganographic approach for 3D Gaussian Splatting (3DGS) that can embed meaningful 3D scene content remains challenging. In this paper, we propose IBRSteG, a generalizable framework for 3DGS steganography that enables undetectable concealment of secret scenes within a steganographic scene. Unlike existing approaches whose parameter generation is rigidly coupled with the specific scene, we formulate 3D steganography as a feed-forward 3D Gaussian embedding process that generalizes across different 3DGS scenes. To realize this, we introduce GAS (Gaussian Attributes Steganographer), a network that learns a scene-independent embedding function by injecting the attributes of secret 3D Gaussian points into a cover scene, thereby directly reconstructing the steganographic scenes without per-scene finetuning or optimization. By transforming 3D Gaussian into these structured attributes, these attributes are compatible with 2D learning paradigms and benefit from their structured nature, thereby enhancing generalization to unseen 3DGS scenes. Extensive experiments on established datasets demonstrate that IBRSteG can effectively conceal different scenes with high visual quality, and achieves superior capacity and security. Code is available at https://github.com/LingXiang2023/IBRSteG.