4 papers
GhostSplat: Input-Triggered Backdoors for Multi-View-Consistent 3D Content Manipulation in Feed-Forward Gaussian Splatting
Yudong Gao, Zongjian Ding, Linghan Chen +5
Feed-forward 3D Gaussian Splatting (3DGS) reconstructs a 3D scene from sparse images in one forward pass. Its shared pretrained weights also expose a supply-chain attack surface. E…
Seed2GS: Camera-Free, Training-Free Object Extraction from 3D Gaussian Scenes via a Single Reference-View Grounding
Zongjian Ding, Yudong Gao, Jiale Liu +7
Extracting a target object from a pre-built 3D Gaussian Splatting (3DGS) scene enables interactive 3D editing. Existing methods either train for tens of minutes per scene, sacrific…
CM-EVS: Sparse Panoramic RGB-D-Pose Data for Complete Scene Coverage
Jiale Liu, Jungang Li, Jieming Yu +13
Modern 3D visual learning relies on observations sampled from metric 3D assets, yet existing scans, meshes, point clouds, simulations, and reconstructions do not directly provide a…
GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting
Changkun Liu, Shuai Chen, Yash Bhalgat +5
We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement (CPR) framework, GS-CPR. This framework enhances the localiz…