SettleSplat: 視野内のシーン変化に対応する単眼ガウシアンマッピング
SettleSplat: Monocular Gaussian Mapping under In-View Scene Changes
カメラ前で物体が動かされる「視野内変化」に対し、不確実性を用いて一時的な動体を除去しつつ恒久的な変化を反映した3Dガウシアンマップを維持する単眼オンラインマッピング手法を提案。
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: Anh Thuan Tran, Xiyun Song, Yubin Zhou, Heather Yu, Jana Kosecka, Liang Peng
分類: cs.CV
原文アブストラクト
Online 3D Gaussian mapping enables fast and high-fidelity novel view synthesis, with broad applications in augmented reality, robotics, and autonomous systems. However, many current methods assume static scenes or filter out dynamics as outliers. In this paper, we study in-view scene changes where objects are manipulated in front of the camera within a single online sequence, unlike prior works that detect changes outside the camera view or between separate captures. This setting entangles transient and persistent dynamics, as objects can be distractors while moving and persistent once they settle. While recent studies start to address distractors by removing them for clean static background, in-view scene changes remain underexplored. To resolve this, we present SettleSplat, a monocular mapping system that maintains up-to-date 3D Gaussian maps under such changes. Specifically, we lift coarse per-pixel uncertainty into Gaussian dynamicity field, then prune transient ones. For persistent changes, we derive geometric contradictions weighted by parameter-free rendered depth uncertainty to separate true changes from under-optimized regions. On Bonn and Co-Fusion, SettleSplat achieves consistent 3D Gaussian maps, outperforming current baselines on both full images and change regions while maintaining comparable speed.