Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring

About

Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce boundary leakage and identity switches. Directly optimizing against these unreliable 2D targets forces the 3D representation to absorb multi-view contradictions, leading to severe error accumulation. To resolve this limitation, we propose SAD-GS, a framework for learning reliable 3D semantic Gaussian fields via dynamic geo-semantic anchoring. Specifically, Semantic Anchor Distillation (SAD) distills per-view visual embeddings into consensus text anchors to establish a viewpoint-invariant semantic identity. Concurrently, the Geo-Semantic Feedback Loop (GSFL) leverages the evolving 3D field to actively filter tracker anomalies and refine spatial mask assignments via a conservative three-gate update rule. Extensive evaluations on LERF-OVS, 3D-OVS, and Mip-NeRF360 show that SAD-GS consistently achieves the best overall performance in both open-vocabulary localization and semantic segmentation. These comprehensive improvements validate the effectiveness and robustness of dynamic geo-semantic anchoring for reliable 3D semantic Gaussian field learning.

Yufei Zhang, Chenlu Zhan, Gaoang Wang, Hongwei Wang• 2026

Related benchmarks

TaskDatasetResultRank
3D Semantic Segmentation3D-OVS
Bed98.4
55
3D Semantic SegmentationLERF-OVS
Ramen Score77.9
8
3D Object LocalizationLERF-OVS
Ramen Score85.8
7
3D Semantic SegmentationMip-NeRF360 sparse scenes
Accuracy (Room)65.2
6
Showing 4 of 4 rows

Other info

Follow for update