MFOS: Model-Free & One-Shot Object Pose Estimation

被引:0
|
作者
Lee, JongMin [1 ]
Cabon, Yohann [2 ]
Bregier, Romain [2 ]
Yoo, Sungjoo [1 ]
Revaud, Jerome [2 ]
机构
[1] Seoul Natl Univ, Seoul, South Korea
[2] Naver Labs Europe, Meylan, France
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Existing learning-based methods for object pose estimation in RGB images are mostly model-specific or category based. They lack the capability to generalize to new object categories at test time, hence severely hindering their practicability and scalability. Notably, recent attempts have been made to solve this issue, but they still require accurate 3D data of the object surface at both train and test time. In this paper, we introduce a novel approach that can estimate in a single forward pass the pose of objects never seen during training, given minimum input. In contrast to existing state-of-the-art approaches, which rely on task-specific modules, our proposed model is entirely based on a transformer architecture, which can benefit from recently proposed 3D-geometry general pretraining. We conduct extensive experiments and report state-of-the-art one-shot performance on the challenging LINEMOD benchmark. Finally, extensive ablations allow us to determine good practices with this relatively new type of architecture in the field.
引用
收藏
页码:2911 / 2919
页数:9
相关论文
共 50 条
  • [1] LWOSNet: A Lightweight One-Shot Network Framework for Object Pose Estimation
    Wang, Chao
    Zang, Xizhe
    Zhang, Xuehe
    Cao, Bin
    Zhou, Lei
    Zhao, Jie
    Ang, Marcelo H., Jr.
    IEEE SENSORS JOURNAL, 2023, 23 (22) : 27624 - 27633
  • [2] OnePose: One-Shot Object Pose Estimation without CAD Models
    Sun, Jiaming
    Wang, Zihao
    Zhang, Siyu
    He, Xingyi
    Zhao, Hongcheng
    Zhang, Guofeng
    Zhou, Xiaowei
    2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022), 2022, : 6815 - 6824
  • [3] MVP: One-Shot Object Pose Estimation by Matching With Visible Points
    Cheng, Wentao
    Luo, Minxing
    IEEE SIGNAL PROCESSING LETTERS, 2024, 31 : 2760 - 2764
  • [4] OnePose plus plus : Keypoint-Free One-Shot Object Pose Estimation without CAD Models
    He, Xingyi
    Sun, Jiaming
    Wang, Yuang
    Huang, Di
    Bao, Hujun
    Zhou, Xiaowei
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [5] One-Shot Imitation Learning: A Pose Estimation Perspective
    Vitiello, Pietro
    Dreczkowski, Kamil
    Johns, Edward
    CONFERENCE ON ROBOT LEARNING, VOL 229, 2023, 229
  • [6] PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matching
    Castro, Pedro
    Kim, Tae-Kyun
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS, ICCVW, 2023, : 2140 - 2149
  • [7] The Vitruvian Manifold: Inferring Dense Correspondences for One-Shot Human Pose Estimation
    Taylor, Jonathan
    Shotton, Jamie
    Sharp, Toby
    Fitzgibbon, Andrew
    2012 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2012, : 103 - 110
  • [8] One-Shot Scale and Angle Estimation for Fast Visual Object Tracking
    Lee, Dong-Hyun
    IEEE ACCESS, 2019, 7 : 55477 - 55484
  • [9] One-Shot Video Object Segmentation
    Caelles, S.
    Maninis, K. -K.
    Pont-Tuset, J.
    Leal-Taixe, L.
    Cremers, D.
    Van Gool, L.
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 5320 - 5329
  • [10] One-shot learning of object categories
    Li, FF
    Fergus, R
    Perona, P
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2006, 28 (04) : 594 - 611