インスタンス非依存の幾何・接触ダイナミクス学習
Instance-Agnostic Geometry and Contact Dynamics Learning
RGBD動画から物体の形状・姿勢・物理特性を同時に学習する枠組みを提案し、視覚とダイナミクスを循環的に統合して追跡精度を向上させた。
著者: Mengti Sun, Bowen Jiang, Bibit Bianchini, Camillo Jose Taylor, Michael Posa
分類: cs.CV, cs.LG, cs.RO
原文アブストラクト
This work presents an instance-agnostic learning framework that fuses vision with dynamics to simultaneously learn shape, pose trajectories, and physical properties via the use of geometry as a shared representation. Unlike many contact learning approaches that assume motion capture input and a known shape prior for the collision model, our proposed framework learns an object's geometric and dynamic properties from RGBD video, without requiring either category-level or instance-level shape priors. We integrate a vision system, BundleSDF, with a dynamics system, ContactNets, and propose a cyclic training pipeline to use the output from the dynamics module to refine the poses and the geometry from the vision module, using perspective reprojection. Experiments demonstrate our framework's ability to learn the geometry and dynamics of rigid and convex objects and improve upon the current tracking framework.
