研究人员开发了GaussDet，一种用于3D高斯溅射（3DGS）场景的开放词汇和指代分割的新颖方法。与以往严重依赖密集CLIP特征或在实例分组方面遇到困难的方法不同，GaussDet利用离散的、开放词汇的2D对象检测器。这使得更鲁棒的语义理解和复杂空间推理成为可能。该方法在开放词汇分割和指代表达式地面化等任务中取得了显著的改进，特别是在零样本设置下，指代地面化任务的mIoU提高了16.7%。 AI
影响 通过提高开放词汇和指代分割能力，增强了3D场景重建和语言驱动的应用。
排序理由 该集群包含一篇关于3D场景理解新方法的arXiv论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.30638v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged at the forefront of 3D scene reconstruction. Extending 3DGS with language-driven, open-vocabulary understanding has gained significant attention for real-world applications such as embodied A…
3D Gaussian Splatting (3DGS) has emerged at the forefront of 3D scene reconstruction. Extending 3DGS with language-driven, open-vocabulary understanding has gained significant attention for real-world applications such as embodied AI. Recent methods achieve this by learning an in…