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
  • [21] Augmentative contrastive learning for one-shot object detection
    Du, Yaoyang
    Liu, Fang
    Jiao, Licheng
    Hao, Zehua
    Li, Shuo
    Liu, Xu
    Liu, Jing
    NEUROCOMPUTING, 2022, 513 : 13 - 24
  • [22] Unreal mask: one-shot multi-object class-based pose estimation for robotic manipulation using keypoints with a synthetic dataset
    Zabihifar, S. H.
    Semochkin, A. N.
    Seliverstova, E. V.
    Efimov, A. R.
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (19): : 12283 - 12300
  • [23] Unreal mask: one-shot multi-object class-based pose estimation for robotic manipulation using keypoints with a synthetic dataset
    S. H. Zabihifar
    A. N. Semochkin
    E. V. Seliverstova
    A. R. Efimov
    Neural Computing and Applications, 2021, 33 : 12283 - 12300
  • [24] One-Shot Object Detection in Heterogeneous Artwork Datasets
    Madhu, Prathmesh
    Meyer, Anna
    Zinnen, Mathias
    Muhrenberg, Lara
    Suckow, Dirk
    Bendschus, Torsten
    Reinhardt, Corinna
    Bell, Peter
    Verstegen, Ute
    Kosti, Ronak
    Maier, Andreas
    Christlein, Vincent
    2022 ELEVENTH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING THEORY, TOOLS AND APPLICATIONS (IPTA), 2022,
  • [25] One-shot categorization of novel object classes in humans
    Morgenstern, Yaniv
    Schmidt, Filipp
    Fleming, Roland W.
    VISION RESEARCH, 2019, 165 : 98 - 108
  • [26] LAPLACIAN OBJECT: ONE-SHOT OBJECT DETECTION BY LOCALITY PRESERVING PROJECTION
    Biswas, Sujoy Kumar
    Milanfar, Peyman
    2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 4062 - 4066
  • [27] Model-free non-rigid head pose tracking by joint shape and pose estimation
    Stefania Cristina
    Kenneth P. Camilleri
    Machine Vision and Applications, 2016, 27 : 1229 - 1242
  • [28] Model-free non-rigid head pose tracking by joint shape and pose estimation
    Cristina, Stefania
    Camilleri, Kenneth P.
    MACHINE VISION AND APPLICATIONS, 2016, 27 (08) : 1229 - 1242
  • [29] One-Shot Replay: Boosting Incremental Object Detection via Retrospecting One Object
    Yang, Dongbao
    Zhou, Yu
    Hong, Xiaopeng
    Zhang, Aoting
    Wang, Weiping
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 3, 2023, : 3127 - 3135
  • [30] SamPose: Generalizable Model-Free 6D Object Pose Estimation via Single-View Prompt
    Shi, Wubin
    Gai, Shaoyan
    Da, Feipeng
    Cai, Zeyu
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2025, 10 (05): : 4420 - 4427