Deep Virtual Markers for Articulated 3D Shapes

Kim, Hyomin; Kim, Jungeon; Kam, Jaewon; Park, Jaesik; Lee, Seungyong

doi:10.1109/iccv48922.2021.01141

Cited by 7 publications

(4 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the flourishing of 3D generative models [4,16,17,25,34,38,49,54,59], implicit representations [8,22,30,39,57] have been widely applied in the generation of digital avatars. 3D-aware GANs [5] have been employed to generate avatars in canonical pose space [3,7,15,60], followed by a deformation module to transform the avatars into various body poses.…”

Section: Introductionmentioning

confidence: 99%

School of Mechanical Engineering, Shanghai Jiao Tong University, 200240, Shanghai, China

Zhuang

Huang

et al. 2019

Mathematical Biosciences and Engineering

View full text Add to dashboard Cite

The crystallization kinetics and melting behavior of nylon 10,10 in neat nylon 10,10 and in nylon 10,10 -montmorillonite (MMT) nanocomposites were systematically investigated by differential scanning calorimetry. The crystallization kinetics results show that the addition of MMT facilitated the crystallization of nylon 10,10 as a heterophase nucleating agent; however, when the content of MMT was high, the physical hindrance of MMT layers to the motion of nylon 10,10 chains retarded the crystallization of nylon 10,10, which was also confirmed by polarized optical microscopy. However, both nylon 10,10 and nylon 10,10 -MMT nanocomposites exhibited multiple melting be-havior under isothermal and nonisothermal crystallization conditions. The temperature of the lower melting peak (peak I) was independent of MMT content and almost remained constant; however, the temperature of the highest melting peak (peak II) decreased with increasing MMT content due to the physical hindrance of MMT layers to the motion of nylon 10,10 chains.

show abstract

Section: Introductionmentioning

confidence: 99%

School of Mechanical Engineering, Shanghai Jiao Tong University, 200240, Shanghai, China

Zhuang

Huang

et al. 2019

Mathematical Biosciences and Engineering

View full text Add to dashboard Cite

show abstract

“…The canonical neutral SMPL model M 𝐶 is in the T-pose, and we align the model with each input point cloud P 𝑡 by estimating shape and pose parameters, 𝜷 and 𝜽 𝑡 , so that the constructed posed skinned body M 𝑡 can fit P 𝑡 well. We apply deep virtual markers [Kim et al 2021] to M 𝐶 and P 𝑡 to obtain the initial geometric correspondence. We additionally use OpenPose [Cao et al 2019] to improve the point matching accuracy if color images are available.…”

Section: Pose-dependent Base Mesh 51 Skinned Body Acquisitionmentioning

confidence: 99%

“…In our LaplacianFusion framework, all reconstructed models have the same fixed topology resulting from the subdivision applied to the SMPL model. Then, we can build a common UV parametric domain for texture mapping of any reconstructed [Kim et al 2021]. Then, the texture of M 𝐶 can be shared with different reconstructed models through the common UV parametric domain.…”

Section: Sourcementioning

confidence: 99%