MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909763136126976 |
|---|---|
| author | Huang, Xiufeng Luo, Ziyuan Song, Qi Wang, Ruofei Wan, Renjie |
| author_facet | Huang, Xiufeng Luo, Ziyuan Song, Qi Wang, Ruofei Wan, Renjie |
| contents | The growing popularity of 3D Gaussian Splatting (3DGS) has intensified the need for effective copyright protection. Current 3DGS watermarking methods rely on computationally expensive fine-tuning procedures for each predefined message. We propose the first generalizable watermarking framework that enables efficient protection of Splatter Image-based 3DGS models through a single forward pass. We introduce GaussianBridge that transforms unstructured 3D Gaussians into Splatter Image format, enabling direct neural processing for arbitrary message embedding. To ensure imperceptibility, we design a Gaussian-Uncertainty-Perceptual heatmap prediction strategy for preserving visual quality. For robust message recovery, we develop a dense segmentation-based extraction mechanism that maintains reliable extraction even when watermarked objects occupy minimal regions in rendered views. Project page: https://kevinhuangxf.github.io/marksplatter. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_00757 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure Huang, Xiufeng Luo, Ziyuan Song, Qi Wang, Ruofei Wan, Renjie Computer Vision and Pattern Recognition The growing popularity of 3D Gaussian Splatting (3DGS) has intensified the need for effective copyright protection. Current 3DGS watermarking methods rely on computationally expensive fine-tuning procedures for each predefined message. We propose the first generalizable watermarking framework that enables efficient protection of Splatter Image-based 3DGS models through a single forward pass. We introduce GaussianBridge that transforms unstructured 3D Gaussians into Splatter Image format, enabling direct neural processing for arbitrary message embedding. To ensure imperceptibility, we design a Gaussian-Uncertainty-Perceptual heatmap prediction strategy for preserving visual quality. For robust message recovery, we develop a dense segmentation-based extraction mechanism that maintains reliable extraction even when watermarked objects occupy minimal regions in rendered views. Project page: https://kevinhuangxf.github.io/marksplatter. |
| title | MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.00757 |