Two-Stage Co-Segmentation Network Based on Discriminative Representation for Recovering Human Mesh From Videos

no code implementations • CVPR 2023 • Boyang Zhang, Kehua Ma, Suping Wu, Zhixiang Yuan

However, most of the existing methods focus on the temporal consistency of videos, while ignoring the spatial representation in complex scenes, thus failing to recover a reasonable and smooth human mesh sequence under extreme illumination and chaotic backgrounds. To alleviate this problem, we propose a two-stage co-segmentation network based on discriminative representation for recovering human body meshes from videos.

Spatio-temporal Tendency Reasoning for Human Body Pose and Shape Estimation from Videos

no code implementations • 7 Oct 2022 • Boyang Zhang, Suping Wu, Hu Cao, Kehua Ma, Pan Li, Lei Lin

Different from them, our STR aims to learn accurate and natural motion sequences in an unconstrained environment through temporal and spatial tendency and to fully excavate the spatio-temporal features of existing video data.

3D Human Pose Estimation Temporal Sequences

DmifNet:3D Shape Reconstruction Based on Dynamic Multi-Branch Information Fusion

1 code implementation • 21 Nov 2020 • Lei LI, Suping Wu

Then, we use a separate side branch network to process the extracted data to better capture edge geometry and corners feature information.

3D Object Reconstruction 3D Shape Reconstruction +1