A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

Standard

A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape. / Li, Zhongguo; Heyden, Anders; Oskarsson, Magnus.

Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Springer, 2021. s. 41-56 ( Lecture Notes in Computer Science; Vol. 12661).

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

Harvard

Li, Z, Heyden, A & Oskarsson, M 2021, A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape. i Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science, vol. 12661, Springer, s. 41-56. https://doi.org/10.1007/978-3-030-68763-2_4

APA

Li, Z., Heyden, A., & Oskarsson, M. (2021). A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape. I Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021 (s. 41-56). ( Lecture Notes in Computer Science; Vol. 12661). Springer. https://doi.org/10.1007/978-3-030-68763-2_4

CBE

Li Z, Heyden A, Oskarsson M. 2021. A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape. I Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Springer. s. 41-56. ( Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-030-68763-2_4

MLA

Li, Zhongguo, Anders Heyden, och Magnus Oskarsson "A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape". Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Lecture Notes in Computer Science. Springer. 2021, 41-56. https://doi.org/10.1007/978-3-030-68763-2_4

Vancouver

Li Z, Heyden A, Oskarsson M. A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape. I Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Springer. 2021. s. 41-56. ( Lecture Notes in Computer Science). https://doi.org/10.1007/978-3-030-68763-2_4

Author

Li, Zhongguo ; Heyden, Anders ; Oskarsson, Magnus. / A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape. Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021. Springer, 2021. s. 41-56 ( Lecture Notes in Computer Science).

RIS

TY - GEN

T1 - A Novel Joint Points and Silhouette-Based Method to Estimate 3D Human Pose and Shape

AU - Li, Zhongguo

AU - Heyden, Anders

AU - Oskarsson, Magnus

PY - 2021

Y1 - 2021

N2 - This paper presents a novel method for 3D human pose and shape estimation from images with sparse views, using joint points and silhouettes, based on a parametric model. Firstly, the parametric model is fitted to the joint points estimated by deep learning-based human pose estimation. Then, we extract the correspondence between the parametric model of pose fitting and silhouettes in 2D and 3D space. A novel energy function based on the correspondence is built and minimized to fit a parametric model to the silhouettes. Our approach uses comprehensive shape information because the energy function of silhouettes is built from both 2D and 3D space. This also means that our method only needs images from sparse views, which balances data used and the required prior information. Results on synthetic data and real data demonstrate the competitive performance of our approach on pose and shape estimation of the human body.

AB - This paper presents a novel method for 3D human pose and shape estimation from images with sparse views, using joint points and silhouettes, based on a parametric model. Firstly, the parametric model is fitted to the joint points estimated by deep learning-based human pose estimation. Then, we extract the correspondence between the parametric model of pose fitting and silhouettes in 2D and 3D space. A novel energy function based on the correspondence is built and minimized to fit a parametric model to the silhouettes. Our approach uses comprehensive shape information because the energy function of silhouettes is built from both 2D and 3D space. This also means that our method only needs images from sparse views, which balances data used and the required prior information. Results on synthetic data and real data demonstrate the competitive performance of our approach on pose and shape estimation of the human body.

U2 - 10.1007/978-3-030-68763-2_4

DO - 10.1007/978-3-030-68763-2_4

M3 - Paper in conference proceeding

SN - 978-3-030-68762-5

T3 - Lecture Notes in Computer Science

SP - 41

EP - 56

BT - Pattern Recognition. ICPR International Workshops and Challenges. ICPR 2021

PB - Springer

ER -