SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring
For 3D scene understanding tasks, this work provides a robust method to mitigate error accumulation from multi-view semantic inconsistencies.
SAD-GS addresses unreliable 2D supervision in open-vocabulary 3D semantic Gaussian field learning by introducing dynamic geo-semantic anchoring, achieving state-of-the-art performance on LERF-OVS, 3D-OVS, and Mip-NeRF360 benchmarks.
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.