OPFormer: 幾何エンコーディングと基盤モデルを活用した物体姿勢推定
OPFormer: Object Pose Estimation leveraging foundation model with geometric encoding
物体検出と6D姿勢推定を統合したフレームワークを提案し、基盤モデルとNOCSによる幾何情報を組み合わせて高精度かつ効率的に姿勢を推定する。
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: Artem Moroz, Vít Zeman, Martin Mikšík, Elizaveta Isianova, Miroslav David, Pavel Burget, Varun Burde
分類: cs.CV, cs.AI, cs.LG, cs.RO
原文アブストラクト
We introduce a unified, end-to-end framework that seamlessly integrates object detection and pose estimation with a versatile onboarding process. Our pipeline begins with an onboarding stage that generates object representations from either traditional 3D CAD models or, in their absence, by rapidly reconstructing a high-fidelity neural representation (NeRF) from multi-view images. Given a test image, our system first employs the CNOS detector to localize target objects. For each detection, our novel pose estimation module, OPFormer, infers the precise 6D pose. The core of OPFormer is a transformer-based architecture that leverages a foundation model for robust feature extraction. It uniquely learns a comprehensive object representation by jointly encoding multiple template views and enriches these features with explicit 3D geometric priors using Normalized Object Coordinate Space (NOCS). A decoder then establishes robust 2D-3D correspondences to determine the final pose. Evaluated on the challenging BOP benchmarks, our integrated system demonstrates a strong balance between accuracy and efficiency, showcasing its practical applicability in both model-based and model-free scenarios.
