English(EN) OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention

OpenGaFF框架通过高斯特征和码本注意力增强3D场景理解

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-07 12:10

研究人员推出OpenGaFF，一个利用3D高斯泼溅技术改进开放词汇3D场景理解的新框架。该系统将语义建模为高斯几何和外观的连续函数，通过将语义预测直接链接到几何结构来增强空间一致性。它还包含一个结构化码本和一个引导注意力机制，以确保对象级别的语义一致性并实现与语言特征的鲁棒推理。 AI

影响增强3D场景理解能力，可能改进机器人和增强现实领域的应用。

排序理由这是一篇详细介绍用于3D场景理解的新颖框架的研究论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.CV TIER_1 English(EN) · Kunyi Li, Michael Niemeyer, Sen Wang, Stefano Gasperini, Nassir Navab, Federico Tombari · 2026-05-08 04:00

OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention

arXiv:2605.06088v1 Announce Type: new Abstract: Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a …
arXiv cs.CV TIER_1 English(EN) · Federico Tombari · 2026-05-07 12:10

OpenGaFF: Open-Vocabulary Gaussian Feature Field with Codebook Attention

Understanding open-vocabulary 3D scenes with Gaussian-based representations remains challenging due to fragmented and spatially inconsistent semantic predictions across multi-view observations. In this paper, we present OpenGaFF, a novel framework for open-vocabulary 3D scene und…