SceneScore: 物体配置のためのコスト関数学習
SceneScore: Learning a Cost Function for Object Arrangement
画像のみから物体配置の望ましさを評価するコスト関数をエネルギーベースモデルとグラフニューラルネットで学習し、欠損物体の姿勢予測や新規物体への汎化、制約付き配置生成を可能にした。
著者: Ivan Kapelyukh, Edward Johns
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
Arranging objects correctly is a key capability for robots which unlocks a wide range of useful tasks. A prerequisite for creating successful arrangements is the ability to evaluate the desirability of a given arrangement. Our method "SceneScore" learns a cost function for arrangements, such that desirable, human-like arrangements have a low cost. We learn the distribution of training arrangements offline using an energy-based model, solely from example images without requiring environment interaction or human supervision. Our model is represented by a graph neural network which learns object-object relations, using graphs constructed from images. Experiments demonstrate that the learned cost function can be used to predict poses for missing objects, generalise to novel objects using semantic features, and can be composed with other cost functions to satisfy constraints at inference time.
