.png){kind=icon}
返回
Weakly-supervised pre-training for 3D human pose estimation via perspective knowledge
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2023.109497.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Modern deep learning-based 3D pose estimation approaches require plenty of 3D pose annotations. How-ever, existing 3D datasets lack diversity, which limits the performance of current methods and their gen-eralization ability. Although existing methods utilize 2D pose annotations to help 3D pose estimation, they mainly focus on extracting 2D structural constraints from 2D poses, ignoring the 3D information hidden in the images. In this paper, we propose a novel method to extract weak 3D information di-rectly from 2D images without 3D pose supervision. Firstly, we utilize 2D pose annotations and perspec-tive prior knowledge to generate the relative depth of human joints. Then, we collect a 2D pose dataset (MCPC) and generate relative depth labels. Based on MCPC, we propose a weakly-supervised pre-training (WSP) strategy to distinguish the depth relationship between two points in an image. WSP enables the learning of the relative depth of two keypoints on lots of in-the-wild images, which is more capable of predicting depth and generalization ability for 3D human pose estimation. After fine-tuning the pose model on 3D pose datasets, WSP achieves state-of-the-art results on two widely-used benchmarks.(c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Human pose estimation
Pre -training
Relative depth
Weakly -supervised
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
分享收藏
分享收藏3D pose estimation and future motion prediction from 2D images基于2D图像的3D姿态估计和未来运动预测.png)
PATTERN RECOGNITIONOAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏
查看更多内容