
YZ
Yufei Zhang, Chenlu Zhan, Hongwei Wang
· 1 min read
ResearcharXiv cs.CV
GaussianDS: Depth-supervised Semantic Gaussian Splatting for Scene Understanding
arXiv:2609.27850v1 Announce Type: new
Abstract: 3D Gaussian Splatting provides an efficient representation for 3D reconstruction, and recent extensions attach semantic attributes to Gaussians for open-vocabulary scene understanding. However, lifting view-dependent 2D foundation-model outputs into 3D space introduces cross-view inconsistencies and weak geometric grounding, leading to severe semantic drift and boundary leakage. We propose GaussianDS, a depth-supervised semantic 3DGS framework that treats semantic lifting as a supervision-alignment problem and jointly optimizes RGB appearance, rendered depth, and compact semantics from scratch. Specifically, GaussianDS organizes unordered multi-view images into a pose-aware pseudo-video trajectory to propagate view-consistent masks via SAM2. During joint optimization, scale-shift-aligned monocular depth supervision and depth total-variation regularization stabilize Gaussian geometry, while a depth-edge-aware refinement loss explicitly anchors semantic transitions onto physical geometric discontinuities. Extensive evaluations show that our end-to-end framework not only retains high-fidelity 3D reconstruction and real-time rendering, but also establishes superior semantic understanding. GaussianDS sets new state-of-the-art performance on LERF (60.5% mIoU) and 3D-OVS (97.79% mIoU, 90.28% mBIoU) by mitigating semantic leakage, while seamlessly facilitating downstream 3D object removal.
Original source
This story was published by arXiv cs.CV and written by Yufei Zhang, Chenlu Zhan, Hongwei Wang. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


