Reproduce “PrinGS: Privacy Preservation in Gaussian Splatting” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Gaurav Behera, Abhinav Raundhal, Archisha Panda, Saumya Balina, Gargi Shroff, Ponnurangam Kumaraguru
PrinGS edits privacy-sensitive content in trained 3D Gaussian Splatting scenes by tracing masked pixels to contributing blobs and blending their appearance with nearby blobs. Post-training editing uses a reference view and mask, not original images. Privacy-by-design tests showed face similarity falling from 83.87% to 9.79%, and detection from 94.74% to 39.47%; OCR-CER reached 1.00 in five tested scenes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.