M Li, H Zhang, Y Zhang, R Shao… - Proceedings of the …, 2024 - openaccess.thecvf.com
Recent years have witnessed a trend of the deep integration of the generation and reconstruction paradigms. In this paper we extend the ability of controllable generative …
We address the problem of regressing 3D human pose and shape from a single image with a focus on 3D accuracy. The current best methods leverage large datasets of 3D pseudo …
Y Ren, X Han, C Zhao, J Wang, L Xu… - Proceedings of the …, 2024 - openaccess.thecvf.com
For human-centric large-scale scenes fine-grained modeling for 3D human global pose and shape is significant for scene understanding and can benefit many real-world applications …
C Zhao, J Zhang, J Du, Z Shan… - Proceedings of the …, 2024 - openaccess.thecvf.com
We are living in a world surrounded by diverse and" smart" devices with rich modalities of sensing ability. Conveniently capturing the interactions between us humans and these …
HE Pang, Z Cai, L Yang, Q Tao, Z Wu… - Advances in Neural …, 2024 - proceedings.neurips.cc
Whole-body pose and shape estimation aims to jointly predict different behaviors (eg, pose, hand gesture, facial expression) of the entire human body from a monocular image. Existing …
W Song, X Zhang, Y Guo, S Li, A Hao, H Qin - International Journal of …, 2023 - Springer
Although novel 3D animation techniques could be boosted by a large variety of deep learning methods, flexible automatic 3D applications (involving animated figures such as …
P Wu, X Lu, J Shen, Y Yin - Proceedings of the 31st ACM international …, 2023 - dl.acm.org
Human mesh reconstruction (HMR) from monocular video is the key step to many mixed reality and robotic applications. Although existing methods show promising results by …
Estimating 3D human mesh is appealing for various application scenarios. Current mainstream solution predicts the meshes either from the image or the human reflected RF …
Marker-less monocular 3D human motion capture (MoCap) with scene interactions is a challenging research topic relevant for extended reality, robotics and virtual avatar …