DM-OSVP++: 3D拡散モデルを用いたRGBベース物体再構成のためのワンショット視点計画
DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstruction
3D拡散モデルを事前情報として活用し、初期の多視点画像から物体の近似モデルを生成して、複雑な部分に焦点を当てた視点を一度に計画する手法を提案。シミュレーションと実世界実験で有効性を検証した。
著者: Sicong Pan, Liren Jin, Xuying Huang, Cyrill Stachniss, Marija Popović, Maren Bennewitz
分類: cs.RO, cs.CV
原文アブストラクト
Active object reconstruction is crucial for many robotic applications. A key aspect in these scenarios is generating object-specific view configurations to obtain informative measurements for reconstruction. One-shot view planning enables efficient data collection by predicting all views at once, eliminating the need for time-consuming online replanning. Our primary insight is to leverage the generative power of 3D diffusion models as valuable prior information. By conditioning on initial multi-view images, we exploit the priors from the 3D diffusion model to generate an approximate object model, serving as the foundation for our view planning. Our novel approach integrates the geometric and textural distributions of the object model into the view planning process, generating views that focus on the complex parts of the object to be reconstructed. We validate the proposed active object reconstruction system through both simulation and real-world experiments, demonstrating the effectiveness of using 3D diffusion priors for one-shot view planning.
