While recent two-stage many-to-one deep learning models have demonstrated
great success in 3D human pose estimation, such models are inefficient ways to
detect 3D key points in a sequential video relative to one-shot and
many-to-many models. Another key drawback of two-stage and many-to-one models
is that errors in the first stage will be passed onto the second stage. In this
paper, we introduce SoloPose, a novel one-shot, many-to-many spatio-temporal
transformer model for kinematic 3D human pose estimation of video. SoloPose is
further fortified by HeatPose, a 3D heatmap based on Gaussian Mixture Model
distributions that factors target key points as well as kinematically adjacent
key points. Finally, we address data diversity constraints with the 3D
AugMotion Toolkit, a methodology to augment existing 3D human pose datasets,
specifically by projecting four top public 3D human pose datasets (Humans3.6M,
MADS, AIST Dance++, MPI INF 3DHP) into a novel dataset (Humans7.1M) with a
universal coordinate system. Extensive experiments are conducted on Human3.6M
as well as the augmented Humans7.1M dataset, and SoloPose demonstrates superior
results relative to the state-of-the-art approaches.

本文介绍了 SoloPose，一种新颖的一次性、多对多的时空转换模型，用于视频中的运动学 3D 人体姿势估计。SoloPose 进一步加强了 HeatPose，一种基于高斯混合模型分布的 3D 热图，它对目标关键点和动力学相邻关键点进行因素分解。最后，我们通过 3D AugMotion 工具包解决了数据多样性限制问题，该方法通过将四个顶级公共 3D 人体姿势数据集（Humans3.6M、MADS、AIST Dance++、MPI INF 3DHP）投影到一个新的数据集（Humans7.1M）中，使用了一个通用的坐标系统。在 Human3.6M 和增强的 Humans7.1M 数据集上进行了大量实验证明，SoloPose 相对于最先进的方法具有优越的结果。

SoloPose: 基于视频数据增强的一次性运动学 3D 人体姿势估计

SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data  Augmentation

Due to balanced accuracy and speed, one-shot models which jointly learn
detection and identification embeddings, have drawn great attention in
multi-object tracking (MOT). However, the inherent differences and relations
between detection and re-identification (ReID) are unconsciously overlooked
because of treating them as two isolated tasks in the one-shot tracking
paradigm. This leads to inferior performance compared with existing two-stage
methods. In this paper, we first dissect the reasoning process for these two
tasks, which reveals that the competition between them inevitably would destroy
task-dependent representations learning. To tackle this problem, we propose a
novel reciprocal network (REN) with a self-relation and cross-relation design
so that to impel each branch to better learn task-dependent representations.
The proposed model aims to alleviate the deleterious tasks competition,
meanwhile improve the cooperation between detection and ReID. Furthermore, we
introduce a scale-aware attention network (SAAN) that prevents semantic level
misalignment to improve the association capability of ID embeddings. By
integrating the two delicately designed networks into a one-shot online MOT
system, we construct a strong MOT tracker, namely CSTrack. Our tracker achieves
the state-of-the-art performance on MOT16, MOT17 and MOT20 datasets, without
other bells and whistles. Moreover, CSTrack is efficient and runs at 16.4 FPS
on a single modern GPU, and its lightweight version even runs at 34.6 FPS. The
complete code has been released at this https URL

为了解决一次性追踪模型中的任务竞争问题，提出了一种具有自身关系和交叉关系设计的新型互惠网络（REN），并引入了一个尺度感知的注意网络（SAAN），将二者整合为一的强大的 MOT 跟踪器 CSTrack，可以在 MOT16，MOT17 ​​和 MOT20 数据集上获得最先进的性能，且高效运行于现代单个 GPU 上。