Phys-Liquid: 透明変形液体の3D形状と体積を推定するための物理情報データセット
Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids
容器の動きで変形する透明液体の3D形状・体積を推定するため、97,200枚の物理シミュレーション画像と3Dメッシュからなるデータセットを構築し、4段階の再構成パイプラインで有効性を検証した。
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: Ke Ma, Yizhou Fang, Jean-Baptiste Weibel, Shuai Tan, Xinggang Wang, Yang Xiao, Yi Fang, Tian Xia
分類: cs.CV, cs.RO
原文アブストラクト
Estimating the geometric and volumetric properties of transparent deformable liquids is challenging due to optical complexities and dynamic surface deformations induced by container movements. Autonomous robots performing precise liquid manipulation tasks, such as dispensing, aspiration, and mixing, must handle containers in ways that inevitably induce these deformations, complicating accurate liquid state assessment. Current datasets lack comprehensive physics-informed simulation data representing realistic liquid behaviors under diverse dynamic scenarios. To bridge this gap, we introduce Phys-Liquid, a physics-informed dataset comprising 97,200 simulation images and corresponding 3D meshes, capturing liquid dynamics across multiple laboratory scenes, lighting conditions, liquid colors, and container rotations. To validate the realism and effectiveness of Phys-Liquid, we propose a four-stage reconstruction and estimation pipeline involving liquid segmentation, multi-view mask generation, 3D mesh reconstruction, and real-world scaling. Experimental results demonstrate improved accuracy and consistency in reconstructing liquid geometry and volume, outperforming existing benchmarks. The dataset and associated validation methods facilitate future advancements in transparent liquid perception tasks. The dataset and code are available at https://dualtransparency.github.io/Phys-Liquid/.
