日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

姿勢推定arXiv:2504.10433

MonoDiff9D: 拡散モデルによる単眼カテゴリレベル9D物体姿勢推定

MonoDiff9D: Monocular Category-Level 9D Object Pose Estimation via Diffusion Model

シェア:XThreadsFacebookLINEはてブBluesky

単眼RGB画像から拡散モデルを用いてカテゴリレベルの9D物体姿勢を推定する手法を提案し、形状事前知識やCADモデルを必要とせずに最先端精度を達成した。

著者: Jian Liu, Wei Sun, Hui Yang, Jin Zheng, Zichen Geng, Hossein Rahmani, Ajmal Mian

分類: cs.CV, cs.RO

原文アブストラクト

Object pose estimation is a core means for robots to understand and interact with their environment. For this task, monocular category-level methods are attractive as they require only a single RGB camera. However, current methods rely on shape priors or CAD models of the intra-class known objects. We propose a diffusion-based monocular category-level 9D object pose generation method, MonoDiff9D. Our motivation is to leverage the probabilistic nature of diffusion models to alleviate the need for shape priors, CAD models, or depth sensors for intra-class unknown object pose estimation. We first estimate coarse depth via DINOv2 from the monocular image in a zero-shot manner and convert it into a point cloud. We then fuse the global features of the point cloud with the input image and use the fused features along with the encoded time step to condition MonoDiff9D. Finally, we design a transformer-based denoiser to recover the object pose from Gaussian noise. Extensive experiments on two popular benchmark datasets show that MonoDiff9D achieves state-of-the-art monocular category-level 9D object pose estimation accuracy without the need for shape priors or CAD models at any stage. Our code will be made public at https://github.com/CNJianLiu/MonoDiff9D.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  3. 3newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI