7 papers
Generating Multi-view Adversarial Examples for Visual Geometry Grounded Transformer
Qi Song, Ziyuan Luo, Haoliang Han +1
The Visual Geometry Grounded Transformer (VGGT) enables unified feed-forward 3D reconstruction from multi-view images. However, deploying such a high-performance model may expose c…
SVGS: Single-View to 3D Object Editing via Gaussian Splatting
Pengcheng Xue, Yan Tian, Qiutao Song +7
Text-driven 3D scene editing has attracted considerable interest due to its convenience and user-friendliness. However, methods that rely on implicit 3D representations, such as Ne…
Creating Blank Canvas Against AI-enabled Image Forgery
Qi Song, Ziyuan Luo, Renjie Wan
AIGC-based image editing technology has greatly simplified the realistic-level image modification, causing serious potential risks of image forgery. This paper introduces a new app…
MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure
Xiufeng Huang, Ziyuan Luo, Qi Song +2
The growing popularity of 3D Gaussian Splatting (3DGS) has intensified the need for effective copyright protection. Current 3DGS watermarking methods rely on computationally expens…
Align 3D Representation and Text Embedding for 3D Content Personalization
Qi Song, Ziyuan Luo, Ka Chun Cheung +2
Recent advances in NeRF and 3DGS have significantly enhanced the efficiency and quality of 3D content synthesis. However, efficient personalization of generated 3D content remains…
Unified Steganography via Implicit Neural Representation
Qi Song, Ziyuan Luo, Xiufeng Huang +2
Digital steganography is the practice of concealing for encrypted data transmission. Typically, steganography methods embed secret data into cover data to create stega data that in…