CVPR2018论文笔记（五）TotalCapture_Part1

这周本应该将前面4个note做一个“内化”，试着做了一段时间我发现，好像真的还不是时候。
无意间看到了一个关于“如何阅读和剖析科研论文，直到编程实现 by Siraj Raval”的视频。
https://www.bilibili.com/video/av26568656
视频中提到的方法还是有很多值得借鉴的地方的。转换思路，重新挑选了一篇文章去读。

Total Capture: A 3D Deformation Model for Tracking

Abstract

We present a unified deformation model for the markerless capture of human movement at multiple scales, including facial expressions, body motion, and hand gestures. An initial model is generated by locally stitching together models of the individual parts of the human body, which we refer to as “Frank”. This model enables the full expression of part movements, including face and hands, by a single seamless model. We capture a dataset of people wearing everyday clothes and optimize the Frank model to create “Adam”: a calibrated model that shares the same skeleton hierarchy as the initial model with a simpler parameterization. Finally, we demonstrate the use of these models for total motion tracking in a multiview setup, simultaneously capturing the large-scale body movements and the subtle face and hand motion of a social group of people.

我们提出了一个统一的形变模型，用于多尺度人体运动的无标记捕获，包括面部表情、身体运动和手势。初始模型是通过局部拼贴人体各个部分的模型而产生的，我们称之为“Frank”。该模型能够通过单个无缝模型充分表达部分运动，包括面部和手部。我们捕获穿着日常服装的人的数据集，并优化Frank模型以创建“Adam”：一个经过校准的模型，该模型共享与初始模型相同的骨架层次，具有简单的参数化。最后，我们论证了在多视图设置中将这些模型用于全运动追踪，同时捕获大规模身体运动以及人类社会群体微妙的脸部和手部的运动。

a simpler parameterization这个地方也查了相关文献，实在想不出更好的表达，mark。

——缓解焦虑最好的办法就是去做让你焦虑的事。