Unsupervised 3D pose transfer with cross consistency and dual reconstruction
The goal of 3D pose transfer is to transfer the pose from the source mesh to the target mesh while preserving the identity information (e.g., face, body shape) of the target mesh. Deep learning-based methods improved the efficiency and performance of 3D pose transfer. However, most of them are train...
Main Authors: | Song, Chaoyue, Wei, Jiacheng, Li, Ruibo, Liu, Fayao, Lin, Guosheng |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Journal Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/172191 |
Similar Items
-
BGaitR-Net: an effective neural model for occlusion reconstruction in gait sequences by exploiting the key pose information
by: Kumar, Somnath Sendhil, et al.
Published: (2024) -
Unsupervised Monocular Depth and Camera Pose Estimation with Multiple Masks and Geometric Consistency Constraints
by: Xudong Zhang, et al.
Published: (2023-06-01) -
Style-Content-Aware Adaptive Normalization Based Pose Guided for Person Image Synthesis
by: Wei Wei, et al.
Published: (2023-01-01) -
A Knowledge Transfer Method for Unsupervised Pose Keypoint Detection Based on Domain Adaptation and CAD Models
by: Fuzhou Du, et al.
Published: (2023-02-01) -
Enhanced 3D Pose Estimation in Multi-Person, Multi-View Scenarios through Unsupervised Domain Adaptation with Dropout Discriminator
by: Junli Deng, et al.
Published: (2023-10-01)