提出像素级语言对齐特征提取方法，提升3D场景理解的精度与效率。
PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding
- 在2D图像中实现像素级语义与语言对齐，保持开放词汇表达能力。
- 通过高效存储与查询机制，大幅减少2D和3D空间中的冗余数据。
- 适用于大规模3D场景理解，兼顾精度与计算效率，适合实际部署。
精确的开放词汇3D场景理解需要兼具语言对齐性和像素级空间精度的语义表征，同时在升维至3D时仍具可扩展性。然而，现有表征难以同时满足这些要求，且将像素级语义密集传播至3D常导致显著冗余，造成大规模场景中存储与查询效率低下。为此，我们提出PLAF（Pixel-wise Language-Aligned Feature extraction）框架，在不牺牲开放词汇表达能力的前提下，实现2D空间中密集而准确的语义对齐。基于该表征，我们进一步设计了一种高效的语义存储与查询方案，显著降低2D与3D域中的冗余。实验表明，PLAF为精确且高效的开放词汇3D场景理解提供了坚实基础。代码已公开于https://github.com/RockWenJJ/PLAF。
原文摘要 · Abstract (English)
Accurate open-vocabulary 3D scene understanding requires semantic representations that are both language-aligned and spatially precise at the pixel level, while remaining scalable when lifted to 3D space. However, existing representations struggle to jointly satisfy these requirements, and densely propagating pixel-wise semantics to 3D often results in substantial redundancy, leading to inefficient storage and querying in large-scale scenes. To address these challenges, we present \emph{PLAF}, a Pixel-wise Language-Aligned Feature extraction framework that enables dense and accurate semantic alignment in 2D without sacrificing open-vocabulary expressiveness. Building upon this representation, we further design an efficient semantic storage and querying scheme that significantly reduces redundancy across both 2D and 3D domains. Experimental results show that \emph{PLAF} provides a strong semantic foundation for accurate and efficient open-vocabulary 3D scene understanding. The codes are publicly available at https://github.com/RockWenJJ/PLAF.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。