LiTe-GS: 3Dガウシアンスプラッティングのためのオラクル効率的な次善視点選択
LiTe-GS: Oracle-Efficient Next Best View Selection for 3D Gaussian Splatting
3Dガウシアンスプラッティングの訓練効率化のため、候補視点をランダムに部分評価することで情報オラクル呼び出しを大幅に削減する次善視点選択手法を提案。
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: Vivek Pandey, Amirhossein Mollaei Khass, Nader Motee
分類: cs.CV, cs.RO
原文アブストラクト
Selecting informative camera views is critical for efficient training and adaptive refinement in 3D Gaussian Splatting, where each observation significantly influences model parameters. However, information-driven view-selection strategies can require repeated evaluations of expensive information-gain oracles as the number of candidate views increases. We propose LiTe-GS, an oracle-efficient method for next best view selection in 3D Gaussian Splatting. LiTe-GS reduces the number of information-oracle evaluations by performing randomized subset evaluation of candidate views rather than exhaustively scoring the full candidate pool. The resulting approach achieves expected $O(M\log(1/ε))$ oracle complexity with respect to the number of candidate views $M$, independent of the selection cardinality $K$, while providing an explicit trade-off between oracle efficiency and approximation quality through $ε$. We provide theoretical guarantees on oracle complexity and approximation performance under the proposed selection scheme. Experiments on Blender and Mip-NeRF 360 demonstrate that LiTe-GS maintains reconstruction quality comparable to Fisher-information-based baselines while substantially reducing the number of Fisher-oracle evaluations across different acquisition settings.