PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction

Computer Science > Computer Vision and Pattern Recognition [Submitted on 14 Apr 2026] PatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction Prajas Wadekar, Venkata Sai Pranav Bachina, Kunal Bhosikar, Ankit Gangwal, Charu Sharma 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. Comments: CVPR Workshop on Security, Privacy, and Adversarial Robustness in 3D Generative Vision Models (SPAR-3D), 2026 Subjects: Computer Vision and Pattern Recognition (cs.CV); Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2604.13153 [cs.CV]   (or arXiv:2604.13153v1 [cs.CV] for this version)   https://doi.org/10.48550/arXiv.2604.13153 Focus to learn more Submission history From: Kunal Bhosikar [view email] [v1] Tue, 14 Apr 2026 18:00:00 UTC (23,654 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CV < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CR cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)