姿勢連続性を考慮した点群表現学習による深度ベースカテゴリレベル6D物体姿勢推定
Learning Point Cloud Representations with Pose Continuity for Depth-Based Category-Level 6D Object Pose Estimation
深度画像のみからカテゴリレベル6D姿勢を推定するHRC-Poseを提案。姿勢の連続性を保つ点群表現を対照学習で獲得し、回転と並進を分離して処理することで高精度かつリアルタイムな推定を実現した。
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: Zhujun Li, Shuo Zhang, Ioannis Stamos
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Category-level object pose estimation aims to predict the 6D pose and 3D size of objects within given categories. Existing approaches for this task rely solely on 6D poses as supervisory signals without explicitly capturing the intrinsic continuity of poses, leading to inconsistencies in predictions and reduced generalization to unseen poses. To address this limitation, we propose HRC-Pose, a novel depth-only framework for category-level object pose estimation, which leverages contrastive learning to learn point cloud representations that preserve the continuity of 6D poses. HRC-Pose decouples object pose into rotation and translation components, which are separately encoded and leveraged throughout the network. Specifically, we introduce a contrastive learning strategy for multi-task, multi-category scenarios based on our 6D pose-aware hierarchical ranking scheme, which contrasts point clouds from multiple categories by considering rotational and translational differences as well as categorical information. We further design pose estimation modules that separately process the learned rotation-aware and translation-aware embeddings. Our experiments demonstrate that HRC-Pose successfully learns continuous feature spaces. Results on REAL275 and CAMERA25 benchmarks show that our method consistently outperforms existing depth-only state-of-the-art methods and runs in real-time, demonstrating its effectiveness and potential for real-world applications. Our code is at https://github.com/zhujunli1993/HRC-Pose.
