3DROID: シーンごとの信頼性を計測したレンダリング可能な3Dガウシアンデータセット
3DROID: A Renderable 3D Gaussian Dataset with Measured Per-Scene Reliability
ロボット操作研究向けに、カメラ外部パラメータの信頼性を考慮して実世界スケールに校正した3Dガウシアン表現のデータセットを構築した。
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: Wonguen Cho, Junhoo Lee, Nojun Kwak
分類: cs.CV, cs.RO
原文アブストラクト
Robot manipulation models primarily reason from 2D observations while acting in the 3D physical world. To bridge this gap, recent work has augmented robot data with geometric priors such as depth, point clouds, and 3D trajectories, while renderable 3D Gaussian representations provide another promising form of 3D supervision. However, 3DGS representation is designed mainly for photometric fidelity and may not preserve real-world metric scale, particularly when the supplied camera extrinsics are unreliable. We study the effect of extrinsic reliability and pose conditioning on feed-forward 3DGS, and propose a calibration-aware pipeline that anchors reconstructed scenes to the robot's metric workspace. Our experiments show that pose conditioning improves novel-view fidelity, while its geometric benefit depends on the reliability of the injected extrinsics. Using this pipeline, we present a renderable, metric-pose-anchored dataset with scene-level reliability information for robot manipulation research. Our dataset is available at https://huggingface.co/datasets/wonguen/3DROID