PatchPoison：污染多视图数据集以降质3D重建
PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction
AI总结：
PatchPoison通过在多视图数据集边缘注入高频率对抗性补丁，干扰SfM管线的特征匹配阶段，从而降低3D重建精度，提供一种无需修改流程的实用预处理方法。
摘要：
3D Gaussian Splatting (3DGS) 近期实现了从随意捕获的多视图图像中进行高度逼真的3D重建。然而，这种可及性引发了隐私问题：公开可用的图像或视频可以被用来在未经同意的情况下重建详细场景或物体的3D模型。我们提出了PatchPoison，一种轻量级的数据集污染方法，以防止未经授权的3D重建。与全局扰动不同，PatchPoison在多视图数据集每个图像的边缘注入一个小的高频率对抗性补丁，即结构化的棋盘图案。该补丁设计用于破坏Structure-from-Motion (SfM) 管线（如COLMAP）的特征匹配阶段，通过引入虚假对应关系，系统性地使估计的相机姿态错位。因此，下游的3DGS优化会偏离正确的场景几何。在NeRF-Synthetic基准上，插入一个12 X 12像素的补丁使LPIPS重建误差增加6.8倍，而被污染的图像对人类观众来说仍然不显眼。PatchPoison不需要流程修改，提供了一种实用的“即插即用”预处理步骤，供内容创作者保护其多视图数据。
英文摘要：
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. Unlike global perturbations, PatchPoison injects a small high-frequency adversarial patch, a structured checkerboard, into the periphery of each image in a multi-view dataset. The patch is designed to corrupt the feature-matching stage of Structure-from-Motion (SfM) pipelines such as COLMAP by introducing spurious correspondences that systematically misalign estimated camera poses. Consequently, downstream 3DGS optimization diverges from the correct scene geometry. On the NeRF-Synthetic benchmark, inserting a 12 X 12 pixel patch increases reconstruction error by 6.8x in LPIPS, while the poisoned images remain unobtrusive to human viewers. PatchPoison requires no pipeline modifications, offering a practical, "drop-in" preprocessing step for content creators to protect their multi-view data.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
