露光統合モーションブラー対応のロボット向け高速オンライン3Dガウシアンスプラッティング
RoMo-GS: Efficient Online 3D Gaussian Splatting for Robot Mapping via Exposure-Integrated Motion Blur
ロボットの高速移動で生じるモーションブラーを露光区間の解析的積分でO(1)処理し、ヘッセ行列ベースの枝刈りでガウシアン数を抑制しつつ、ポーズ・速度・ガウシアンを同時最適化するオンライン3DGSシステムを提案した。
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: Sangwoo Jung, Di Deng, Jiahui Fu, Laura Herlant, Ayoung Kim, Yafei Hu
分類: cs.RO
原文アブストラクト
Online 3D Gaussian Splatting (3DGS) is emerging as a practical way to build a representation for robotics applications. However, deploying it on real-world platforms exposes multiple challenges. Rapid maneuvers of a robot induce motion-blurred images, which corrupt the reconstructed geometry and cause camera pose drift. Furthermore, the number of Gaussians grows without bound during continuous online mapping. In this study, we present RoMo-GS, an online 3DGS system designed to address these challenges. Instead of averaging N discrete sub-frames as in prior motion blur-aware 3DGS, we analytically integrate each projected Gaussian over the exposure interval, yielding an O(1) complexity per Gaussian. Building on this, we bound the Gaussians' growth with a Hessian-based pruning score, while jointly refining pose, velocity, and Gaussians with Adam and an online LM step over the Gaussians. On multiple public datasets and a self-collected dataset, RoMo-GS matches or exceeds offline deblurring 3DGS methods in rendering quality while running 15--150x faster, and operates online at competitive quality with about 20% fewer Gaussians than the online 3DGS baseline.