AI RESEARCH
Robust Prior-Guided Segmentation for Editable 3D Gaussian Splatting
arXiv CS.AI
•
ArXi:2605.16065v1 Announce Type: cross 3D Gaussian Splatting (3D-GS) enables real-time 3D scene reconstruction but lacks robust segmentation for editing tasks such as object removal, extraction, and recoloring. Existing approaches that lift 2D segmentations to the 3D domain suffer from view inconsistencies and coarse masks. In this paper, we propose a novel framework that leverages the Segment Anything Model High Quality (SAM-HQ) to generate accurate 2D masks, addressing the limitations of the standard SAM in boundary fidelity and fine-structure preservation.