论文标题
用原型记忆追逐单眼3D人类重建的尾巴
Chasing the Tail in Monocular 3D Human Reconstruction with Prototype Memory
论文作者
论文摘要
深度神经网络在单像3D人类重建方面取得了巨大进展。但是，现有方法在预测稀有姿势方面仍然缺乏。原因是，大多数当前模型基于单个人类原型进行回归，该原型类似于常见姿势，而远离稀有姿势。在这项工作中，我们1）识别和分析此学习障碍，2）提出了一个原型内存功能增强网络PM-NET，从而有效地改善了预测稀有姿势的性能。我们框架的核心是一个记忆模块，该模块可以学习并存储一组3D人类原型，以捕获常见姿势或稀有姿势的局部分布。通过此公式，回归始于更好的初始化，这相对容易收敛。与其他最新方法相比，对几个广泛使用的数据集进行了广泛的实验证明了该框架的有效性。值得注意的是，我们的方法显着改善了模型对稀有姿势的性能，同时在其他样品上产生可比的结果。
Deep neural networks have achieved great progress in single-image 3D human reconstruction. However, existing methods still fall short in predicting rare poses. The reason is that most of the current models perform regression based on a single human prototype, which is similar to common poses while far from the rare poses. In this work, we 1) identify and analyze this learning obstacle and 2) propose a prototype memory-augmented network, PM-Net, that effectively improves performances of predicting rare poses. The core of our framework is a memory module that learns and stores a set of 3D human prototypes capturing local distributions for either common poses or rare poses. With this formulation, the regression starts from a better initialization, which is relatively easier to converge. Extensive experiments on several widely employed datasets demonstrate the proposed framework's effectiveness compared to other state-of-the-art methods. Notably, our approach significantly improves the models' performances on rare poses while generating comparable results on other samples.
