无监督学习物体姿态先验，提升遮挡情况下的姿态估计精度
Pose Prior Learner: Unsupervised Categorical Prior Learning for Pose Estimation
- 用分层记忆存储典型姿态组件，自监督学习通用姿态先验
- 在人体和动物数据集上优于现有方法，遮挡图像表现更优
- 适合无标注数据场景，可直接用于姿态精修与重建
先验代表对系统的信念或假设，有助于推断与决策。本文提出姿态估计中的无监督类别先验学习挑战，即通过自监督方式从图像中学习任意物体类别的通用姿态先验。尽管先验能有效提升姿态估计性能，但其获取困难。我们提出一种新方法——姿态先验学习器（Pose Prior Learner, PPL），利用分层记忆存储典型姿态的组合部件，从中提炼通用姿态先验。该先验通过模板变换与图像重建提升姿态估计准确率。PPL无需额外人工标注或干预，即可学习有意义的姿态先验，在人体与动物姿态估计数据集上均优于竞争基线。实验表明，使用学习到的典型姿态先验，在遮挡图像上仍具显著有效性。通过迭代推断，PPL利用姿态先验将估计姿态逐步回归至记忆中的典型姿态。代码、模型与数据已公开于：https://github.com/ZhangLab-DeepNeuroCogLab/Pose-Prior-Learner。
原文摘要 · Abstract (English)
A prior represents a set of beliefs or assumptions about a system, aiding inference and decision-making. In this paper, we introduce the challenge of unsupervised categorical prior learning in pose estimation, where AI models learn a general pose prior for an object category from images in a self-supervised manner. Although priors are effective in estimating pose, acquiring them can be difficult. We propose a novel method, named Pose Prior Learner (PPL), to learn a general pose prior for any object category. PPL uses a hierarchical memory to store compositional parts of prototypical poses, from which we distill a general pose prior. This prior improves pose estimation accuracy through template transformation and image reconstruction. PPL learns meaningful pose priors without any additional human annotations or interventions, outperforming competitive baselines on both human and animal pose estimation datasets. Notably, our experimental results reveal the effectiveness of PPL using learned prototypical poses for pose estimation on occluded images. Through iterative inference, PPL leverages the pose prior to refine estimated poses, regressing them to any prototypical poses stored in memory. Our code, model, and data are publicly available at: https://github.com/ZhangLab-DeepNeuroCogLab/Pose-Prior-Learner.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。