DEGauss: Defending Against Malicious 3DEditing for Gaussian Splatting

Neural Information Processing Systems 

Existing 2D defense approaches mainly focus on adding perturbations to single image to resist malicious image editing. However, there remain two limitations when applied directly to 3D scenes: (1) These methods fail to reflect 3D spatial correlations, thus protecting ineffectively under multiple viewpoints.

Duplicate Docs Excel Report

Title
None found

Similar Docs  Excel Report  more

TitleSimilaritySource
None found