Search papers, labs, and topics across Lattice.
This paper introduces OutLangSplat, a novel approach that integrates open-vocabulary language features into 3D Gaussian Splatting specifically for UAV outdoor scenes, addressing the limitations of existing methods that struggle with occlusions and long-distance viewpoints. By employing a dual-branch representation for enhanced spatial consistency and a training-free aggregation strategy that prioritizes reliable pixel contributions, OutLangSplat significantly improves semantic activation accuracy in challenging environments. Experimental results show that OutLangSplat surpasses state-of-the-art techniques in both open-vocabulary semantic segmentation and instance localization tasks, while also providing a new annotated dataset for further research.
OutLangSplat achieves unprecedented accuracy in 3D scene understanding for UAV outdoor environments, overcoming challenges that have stymied previous methods.
3D Language Gaussian Splatting embeds open-vocabulary language features into 3D Gaussian Splatting, providing an efficient explicit representation for text-driven 3D scene understanding. However, existing methods are limited to indoor or small-scale scenes, and tend to fail in Unmanned Aerial Vehicle (UAV) outdoor scenes, where severe occlusions and long distance viewpoints often lead to incorrect semantic activations and missing target responses. In this paper, we present OutLangSplat which adapts language Gaussian representations to UAV outdoor scenes by improving feature representation and aggregation reliability. For the feature representation, a 2D-3D dual-branch representation with region-based alignment and fusion is designed to improve spatial consistency, reducing incomplete target responses and background misactivations. For the feature aggregation, we introduce a training-free contribution and consistency-aware Gaussian feature aggregation strategy that leverages pixel contribution reliability and cross-view semantic consistency to suppress unreliable responses from noisy viewpoints. A new dataset is provided by manually annotating various objects on four real-world public UAV outdoor scene datasets. To the best of our knowledge, it is the first accessible dataset of open-vocabulary 3D scene understanding for UAV outdoor scenes. Quantitative evaluations and ablation studies demonstrate that OutLangSplat outperforms SOTA methods on both open-vocabulary semantic segmentation and instance localization tasks. The datasets and codes will be open-sourced.
