GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting

• URL: http://arxiv.org/abs/2411.19895v5
• Date: Mon, 17 Mar 2025 16:33:17 GMT
• Title: GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
• Authors: Zixuan Chen, Guangcong Wang, Jiahao Zhu, Jianhuang Lai, Xiaohua Xie,
• Abstract summary: GuardSplat is an innovative and efficient framework for watermarking 3DGS assets.<n>Message Embedding module seamlessly embeds messages into the SH features of each 3D Gaussian while preserving the original 3D structure.<n>Anti-distortion Message Extraction module improves robustness against various distortions.
• Score: 70.81218231206617
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) has recently created impressive 3D assets for various applications. However, considering security, capacity, invisibility, and training efficiency, the copyright of 3DGS assets is not well protected as existing watermarking methods are unsuited for its rendering pipeline. In this paper, we propose GuardSplat, an innovative and efficient framework for watermarking 3DGS assets. Specifically, 1) We propose a CLIP-guided pipeline for optimizing the message decoder with minimal costs. The key objective is to achieve high-accuracy extraction by leveraging CLIP's aligning capability and rich representations, demonstrating exceptional capacity and efficiency. 2) We tailor a Spherical-Harmonic-aware (SH-aware) Message Embedding module for 3DGS, seamlessly embedding messages into the SH features of each 3D Gaussian while preserving the original 3D structure. This enables watermarking 3DGS assets with minimal fidelity trade-offs and prevents malicious users from removing the watermarks from the model files, meeting the demands for invisibility and security. 3) We present an Anti-distortion Message Extraction module to improve robustness against various distortions. Experiments demonstrate that GuardSplat outperforms state-of-the-art and achieves fast optimization speed. Project page is at https://narcissusex.github.io/GuardSplat, and Code is at https://github.com/NarcissusEx/GuardSplat.

Related papers

• GS-Marker: Generalizable and Robust Watermarking for 3D Gaussian Splatting [17.880821149078066]
  We propose a single-pass watermarking approach for 3D Gaussian Splatting (3DGS), a well-known yet underexplored representation for watermarking. Our framework, named GS-Marker, incorporates a 3D encoder to embed messages, distortion layers to enhance resilience against various distortions, and a 2D decoder to extract watermarks from renderings.
  arXiv  Detail & Related papers  (2025-03-24T14:29:14Z)
• CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting [3.6711067779088555]
  3DGS relies on millions of Gaussians, which require gigabytes of storage, efficient transfer and storage require compression. Existing 3DGS watermarking methods are vulnerable to quantization-based compression, often resulting in the loss of the embedded watermark. We propose a novel watermarking method that ensures watermark robustness after model compression while maintaining high rendering quality.
  arXiv  Detail & Related papers  (2025-03-17T05:32:15Z)
• X-SG$^2$S: Safe and Generalizable Gaussian Splatting with X-dimensional Watermarks [53.976082636337374]
  We propose a new framework X-SG$2$S which can simultaneously watermark 1 to 3D messages while keeping the original 3DGS scene almost unchanged. X-SG$2$S is the first to unify 1 to 3D watermarking model for 3DGS and the first framework to add multi-modal watermarks simultaneous in one 3DGS.
  arXiv  Detail & Related papers  (2025-02-13T17:59:15Z)
• CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting [88.24743308058441]
  We present CLIP-GS, a novel multimodal representation learning framework grounded in 3DGS. We develop an efficient way to generate triplets of 3DGS, images, and text, facilitating CLIP-GS in learning unified multimodal representations.
  arXiv  Detail & Related papers  (2024-12-26T09:54:25Z)
• WATER-GS: Toward Copyright Protection for 3D Gaussian Splatting via Universal Watermarking [44.335142946449245]
  WATER-GS is a novel method designed to protect 3DGS copyrights through a universal watermarking strategy. We introduce a pre-trained watermark decoder, treating raw 3DGS generative modules as potential watermarks to ensure imperceptibility. We implement novel 3D distortion layers to enhance the robustness of the embedded watermark against common real-world distortions of point cloud data.
  arXiv  Detail & Related papers  (2024-12-07T16:44:22Z)
• Splats in Splats: Embedding Invisible 3D Watermark within Gaussian Splatting [28.790625685438677]
  WaterGS is the first 3DGS watermarking framework that embeds 3D content in 3DGS itself without modifying any attributes of the vanilla 3DGS. Tests indicate that WaterGS significantly outperforms existing 3D steganography techniques, with 5.31% higher scene fidelity and 3X faster rendering speed.
  arXiv  Detail & Related papers  (2024-12-04T08:40:11Z)
• GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting [41.90891053671943]
  Digital watermarking techniques can be applied to embed ownership information discreetly within 3DGS models. Naively embedding the watermark on a pre-trained 3DGS can cause obvious distortion in rendered images. We propose an uncertainty-based method that constrains the perturbation of model parameters to achieve invisible watermarking for 3DGS.
  arXiv  Detail & Related papers  (2024-10-31T08:08:54Z)
• Poison-splat: Computation Cost Attack on 3D Gaussian Splatting [90.88713193520917]
  We reveal a significant security vulnerability that has been largely overlooked in 3DGS. The adversary can poison the input images to drastically increase the computation memory and time needed for 3DGS training. Such a computation cost attack is achieved by addressing a bi-level optimization problem.
  arXiv  Detail & Related papers  (2024-10-10T17:57:29Z)
• Towards Secure and Usable 3D Assets: A Novel Framework for Automatic Visible Watermarking [11.176240030501184]
  3D models, particularly AI-generated ones, have witnessed a recent surge across various industries such as entertainment. We rigorously define the novel task of automated 3D visible watermarking in terms of two competing aspects: watermark quality and asset utility. We propose a method of embedding visible watermarks that automatically determines the right location, orientation, and number of watermarks to be placed on arbitrary 3D assets.
  arXiv  Detail & Related papers  (2024-08-31T00:52:29Z)
• GS-Hider: Hiding Messages into 3D Gaussian Splatting [18.16759704305008]
  3D Gaussian Splatting (3DGS) has already become the emerging research focus in the fields of 3D scene reconstruction and novel view synthesis. It is crucial to protect the copyright, integrity, and privacy of such 3D assets. We propose a steganography framework for 3DGS, dubbed GS-Hider, which can embed 3D scenes and images into original GS point clouds.
  arXiv  Detail & Related papers  (2024-05-24T00:18:15Z)
• SAGS: Structure-Aware 3D Gaussian Splatting [53.6730827668389]
  We propose a structure-aware Gaussian Splatting method (SAGS) that implicitly encodes the geometry of the scene. SAGS reflects to state-of-the-art rendering performance and reduced storage requirements on benchmark novel-view synthesis datasets.
  arXiv  Detail & Related papers  (2024-04-29T23:26:30Z)
• GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
  We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system. Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
  arXiv  Detail & Related papers  (2023-11-20T12:08:23Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.