遮蔽下における生成事前分布と接触誘導制約を用いた物体再構成
Object Reconstruction under Occlusion with Generative Priors and Contact-induced Constraints
生成モデルの形状事前分布と接触情報による境界制約を組み合わせ、遮蔽された物体の3D形状をより正確に再構成する手法を提案。
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: Minghan Zhu, Zhiyi Wang, Qihang Sun, Maani Ghaffari, Michael Posa
分類: cs.CV, cs.RO
原文アブストラクト
Object geometry is key information for robot manipulation. Yet, object reconstruction is a challenging task because cameras only capture partial observations of objects, especially when occlusion occurs. In this paper, we leverage two extra sources of information to reduce the ambiguity of vision signals. First, generative models learn priors of the shapes of commonly seen objects, allowing us to make reasonable guesses of the unseen part of geometry. Second, contact information, which can be obtained from videos and physical interactions, provides sparse constraints on the boundary of the geometry. We combine the two sources of information through contact-guided 3D generation. The guidance formulation is inspired by drag-based editing in generative models. Experiments on synthetic and real-world data show that our approach improves the reconstruction compared to pure 3D generation and contact-based optimization.
