Dynamic Projected Segmentation Networks For Hand Pose Estimation

Che, Yunlong; Qi, Yue

doi:10.1109/icpr.2018.8546330

Cited by 4 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Segmentation in pose estimation. Segmentation has been used in 3D hand pose estimation, 3D human pose estimation and hand tracking and can be grouped into four categories: as a localization step [2,21,37,38,59,61], as a training loss [3,5], as an optimization term [7,35,56], or as an intermediate representation [8,36,41,44,58]. Most single hand pose estimation approaches follow Zimmermann et al [61] in localizing a hand in an image by predicting the hand silhouette, which is used to crop the input image before performing pose estimation.…”

Section: Related Workmentioning

confidence: 99%

Learning To Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation

Fan

Spurr

Kocabas

et al. 2021

2021 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

https://zc-alexfan.github.io/digit Figure 1. When estimating the 3D pose of interacting hands, state-of-the-art methods struggle to disambiguate the appearance of the two hands and their parts. In this example, the baseline fails to differentiate the left and the right wrists (1.1), resulting in erroneous pose estimation (1.2). Our model, DIGIT, reduces the ambiguity by predicting and leveraging a probabilistic part segmentation volume (2.1) to produce reliable pose estimates even when the two hands are in direct contact and under significant occlusion (2.2, 2.3).

show abstract

Section: Related Workmentioning

confidence: 99%

Learning To Disambiguate Strongly Interacting Hands via Probabilistic Per-Pixel Part Segmentation

Fan

Spurr

Kocabas

et al. 2021

2021 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

show abstract

“…Segmentation in pose estimation. Segmentation has been used in 3D hand pose estimation, 3D human pose estimation and hand tracking and can be grouped into four categories: as a localization step [1,19,34,35,56,58], as a training loss [2,4], as an optimization term [6,33,53], or as an intermediate representation [38,41,55]. Most single hand pose estimation approaches follow Zimmermann et al [58] in localizing a hand in an image by predicting the hand silhouette, which is used to crop the input image before performing pose estimation.…”

Section: Related Workmentioning

confidence: 99%

Learning to Disambiguate Strongly Interacting Hands via Probabilistic Per-pixel Part Segmentation

Fan¹,

Spurr²,

Kocabas³

et al. 2021

Preprint

View full text Add to dashboard Cite

Figure 1. When estimating the 3D pose of interacting hands, state-of-the-art methods struggle to disambiguate the appearance of the two hands and their parts. In this example, significant uncertainty between the left and right wrist arise (1.1), resulting in erroneous pose estimation (1.2). Our model, DIGIT, reduces the ambiguity by predicting and leveraging a probabilistic part segmentation volume (2.1) to produce reliable pose estimates even when the two hands are in direct contact and under significant occlusion (2.2, 2.3).

show abstract

“…还有一些方法试图引入刚体动力学 [80][81] 、高斯混合模型 [82][83] 估计手部姿态. Melax 等 [80] 采用基于物理模拟的方法对手部模型和深度点云的配准, 使用除了传统的二维图像作为神经网络的输入外, 还有尝试采用其他方式表示深度图像的工作 [89][90][91] .…”

Section: 在产业界基于主动红外立体视觉的unclassified