CVAM-Pose：用于多目标单目位姿估计的条件变分自编码器
CVAM-Pose: Conditional Variational Autoencoder for Multi-Object Monocular Pose Estimation
AI总结：
本文提出CVAM-Pose方法，通过标签嵌入条件变分自编码器在低维潜在空间实现多目标单目位姿估计，无需依赖3D模型与深度数据，在Linemod-Occluded数据集上表现优于现有潜在空间方法并媲美依赖3D模型的方法。
摘要：
估计刚性物体的位姿是计算机视觉中的基本问题之一，在自动化和增强现实等领域有广泛应用。现有大多数方法采用每个目标类别一个网络的策略，严重依赖目标的3D模型、深度数据，并使用耗时的迭代细化，这对某些应用而言可能不切实际。本文提出了一种用于多目标单目位姿估计的新方法CVAM-Pose，以解决这些局限性。CVAM-Pose方法采用标签嵌入的条件变分自编码器网络，在单一的低维潜在空间中隐式抽象多目标的正则化表示。该自编码过程仅使用投影相机捕获的图像，且对目标遮挡和场景杂乱具有鲁棒性。目标类别采用独热编码并在整个网络中嵌入。所提出的标签嵌入位姿回归策略利用连续位姿表示来解释学习到的潜在空间表示。消融实验和系统评估证明了CVAM-Pose方法在多目标场景中的可扩展性和高效性。该方法优于竞争的潜在空间方法。例如，在Linemod-Occluded数据集上使用 $\mathrm{AR_{VSD}}$ 指标评估时，它分别比AAE和Multi-Path方法好25%和20%。它还取得了与BOP挑战中依赖3D模型的方法相当的结果。代码获取：https://github.com/JZhao12/CVAM-Pose
英文摘要：
Estimating rigid objects' poses is one of the fundamental problems in computer vision, with a range of applications across automation and augmented reality. Most existing approaches adopt one network per object class strategy, depend heavily on objects' 3D models, depth data, and employ a time-consuming iterative refinement, which could be impractical for some applications. This paper presents a novel approach, CVAM-Pose, for multi-object monocular pose estimation that addresses these limitations. The CVAM-Pose method employs a label-embedded conditional variational autoencoder network, to implicitly abstract regularised representations of multiple objects in a single low-dimensional latent space. This autoencoding process uses only images captured by a projective camera and is robust to objects' occlusion and scene clutter. The classes of objects are one-hot encoded and embedded throughout the network. The proposed label-embedded pose regression strategy interprets the learnt latent space representations utilising continuous pose representations. Ablation tests and systematic evaluations demonstrate the scalability and efficiency of the CVAM-Pose method for multi-object scenarios. The proposed CVAM-Pose outperforms competing latent space approaches. For example, it is respectively 25% and 20% better than AAE and Multi-Path methods, when evaluated using the $\mathrm{AR_{VSD}}$ metric on the Linemod-Occluded dataset. It also achieves results somewhat comparable to methods reliant on 3D models reported in BOP challenges. Code available: https://github.com/JZhao12/CVAM-Pose
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
