S-MUSt3R: スライディングマルチビュー3次元再構成
S-MUSt3R: Sliding Multi-view 3D Reconstruction
大規模なRGB動画から単眼3次元再構成を行うため、基盤モデルMUSt3Rを再学習なしで拡張し、系列分割とループ閉じ込め最適化で長いシーケンスに対応させた手法。
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: Leonid Antsfeld, Boris Chidlovskii, Yohann Cabon, Vincent Leroy, Jerome Revaud
分類: cs.CV, cs.RO
原文アブストラクト
The recent paradigm shift in 3D vision led to the rise of foundation models with remarkable capabilities in 3D perception from uncalibrated images. However, extending these models to large-scale RGB stream 3D reconstruction remains challenging due to memory limitations. This work proposes S-MUSt3R, a simple and efficient pipeline that extends the limits of foundation models for monocular 3D reconstruction. Our approach addresses the scalability bottleneck of foundation models through a simple strategy of sequence segmentation followed by segment alignment and lightweight loop closure optimization. Without model retraining, we benefit from remarkable 3D reconstruction capacities of MUSt3R model and achieve trajectory and reconstruction performance comparable to traditional methods with more complex architecture. We evaluate S-MUSt3R on TUM, 7-Scenes and proprietary robot navigation datasets and show that S-MUSt3R runs successfully on long RGB sequences and produces accurate and consistent 3D reconstruction. Our results highlight the potential of leveraging the MUSt3R model for scalable monocular 3D scene in real-world settings, with an important advantage of making predictions directly in the metric space.
