異方性可視性場による不確実性駆動の3Dガウシアンスプラッティング能動マッピング
Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
3Dガウシアンスプラッティング(3DGS)の未観測領域の不確実性を定量化する異方性可視性場を導入し、能動マッピングを実時間で行う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: Shangjie Xue, Jesse Dill, Dhruv Ahuja, Frank Dellaert, Panagiotis Tsiotras, Danfei Xu
分類: cs.CV, cs.RO
原文アブストラクト
We present Gaussian Splatting Anisotropic Visibility Field (GAVIS), a novel framework for uncertainty quantification and active mapping in 3DGS. Our key insight is that regions unseen from the training views yield unreliable predictions from the 3DGS. To address this, we introduce a principled and efficient method for quantifying the visibility field in 3DGS, defined as the anisotropic visibility of each particle with respect to the training views, and represented using spherical harmonics. The resulting visibility field is integrated into a Bayesian Network-based uncertainty-aware 3DGS rasterizer, enabling real-time (200 FPS) uncertainty quantification for synthesized views. Active mapping is further performed within a maximum information gain framework building on this formulation. Extensive experiments across diverse environments demonstrate that GAVIS consistently and significantly outperforms prior approaches in both accuracy and efficiency. Moreover, beyond standalone use, our method can be applied post-hoc to improve the performance of existing approaches.
