SG-GS uses SAM semantics to steer densification in fine-grained urban reconstructions

arXivarXivPapers

SG-GS uses SAM semantics to steer densification in fine-grained urban reconstructions
arXiv / Yueling Liao, San Jiang and colleagues

Yueling Liao, San Jiang, Xing Zhang and Zhongwen Hu present SG-GS, a semantic-guided 3D Gaussian Splatting method for fine-grained urban structures. The approach takes Segment Anything Model (SAM) segmentation as a constraint, assigning gradient thresholds by semantic region and adding a boundary-enhanced densification strategy so new Gaussians are directed to structurally critical areas.

A multi-feature loss is introduced gradually through phased training, which the authors say reduces artifacts that appear when the basic 3DGS loss lacks semantic constraints. On three datasets, they report that PSNR rises by approximately 2.7% to 5.2% compared with the original 3DGS, with fewer artifacts on linear structures and less boundary blur.