PLAF: ピクセル単位の言語整合特徴抽出による効率的な3Dシーン理解
PLAF: Pixel-wise Language-Aligned Feature Extraction for Efficient 3D Scene Understanding
2Dでピクセル単位の高精度な言語整合特徴を抽出し、冗長性を削減する効率的な保存・検索方式を設計することで、オープンボキャブラリ3Dシーン理解を実現するフレームワークを提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Junjie Wen, Junlin He, Fei Ma, Jinqiang Cui
分類: cs.CV, cs.RO
原文アブストラクト
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.
