arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2007.09590cs.CVcs.LGeess.IV
收藏

AWR:自适应加权回归三维手位估计

AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation

Beijing University of Posts and Telecommunications(北京邮电大学);EBUPT Information Technology Co., Ltd.(东信北邮信息技术有限公司)

Weiting Huang, Pengfei Ren, Jingyu Wang, Qi Qi, Haifeng Sun

摘要:

在本文中,我们提出了一种自适应加权回归(AWR)方法,以利用基于检测和基于回归的方法的优点。手关节坐标估计为离散积分的所有像素在密集表示,自适应权重映射的指导下。这种可学习的聚合过程引入了密集和联合监督,允许端到端训练,并为权重图带来适应性,使网络更加准确和强大。综合探索实验进行了各种实验设置下,AWR的有效性和通用性,特别是它的有用性,不同类型的密集表示和输入模态。我们的方法在四个公开可用的数据集上优于其他最先进的方法,包括NYU,ICVL,MSRA和HANDS 2017数据集。

英文摘要:

In this paper, we propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based and regression-based methods. Hand joint coordinates are estimated as discrete integration of all pixels in dense representation, guided by adaptive weight maps. This learnable aggregation process introduces both dense and joint supervision that allows end-to-end training and brings adaptability to weight maps, making the network more accurate and robust. Comprehensive exploration experiments are conducted to validate the effectiveness and generality of AWR under various experimental settings, especially its usefulness for different types of dense representation and input modality. Our method outperforms other state-of-the-art methods on four publicly available datasets, including NYU, ICVL, MSRA and HANDS 2017 dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑