3D Object Instance Recognition And Pose Estimation Using Triplet Loss With Dynamic Margin

Abstract

In this paper, we address the problem of 3D object instance recognition and pose estimation of localized objects in cluttered environments using convolutional neural networks. Inspired by the descriptor learning approach of Wohlhart et al., we propose a method that introduces the dynamic margin in the manifold learning triplet loss function. Such a loss function is designed to map images of different objects under different poses to a lower-dimensional, similarity-preserving descriptor space on which efficient nearest neighbor search algorithms can be applied. Introducing the dynamic margin allows for faster training times and better accuracy of the resulting low-dimensional manifolds. Furthermore, we contribute the following: adding in-plane rotations (ignored by the baseline method) to the training, proposing new background noise types that help to better mimic realistic scenarios and improve accuracy with respect to clutter, adding surface normals as another powerful image modality

Stats

• citations36
• S2 citations—
• github stars0
• HF likes0
• heat score11.76
• arxiv keyzakharov20193d

Related papers

• When Regression Meets Manifold Learning For Object Recognition And Pose Estimation (2018)10.07
• Triplet-center Loss For Multi-view 3D Object Retrieval (2018)18.70
• Neighborhood Watch: Representation Learning With Local-margin Triplet Loss And Sampling Strategy For K-nearest-neighbor Image Classification (2019)0.00
• Deeppoint3d: Learning Discriminative Local Descriptors Using Deep Metric Learning On 3D Point Clouds (2019)9.59
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Sdgmnet: Statistic-based Dynamic Gradient Modulation For Local Descriptor Learning (2021)2.26
• Enhancing Remote Sensing Image Retrieval With Triplet Deep Metric Learning Network (2019)14.58
• Robust Angular Local Descriptor Learning (2019)3.58