AI RESEARCH
PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction
arXiv CS.LG
•
ArXi:2604.13153v1 Announce Type: cross 3D Gaussian Splatting (3DGS) has recently enabled highly photorealistic 3D reconstruction from casually captured multi-view images. However, this accessibility raises a privacy concern: publicly available images or videos can be exploited to reconstruct detailed 3D models of scenes or objects without the owner's consent. We present PatchPoison, a lightweight dataset-poisoning method that prevents unauthorized 3D reconstruction.