Search Results - "Shan, Wenkang"

Improving Robustness and Accuracy via Relative Information Encoding in 3D Human Pose Estimation by Shan, Wenkang, Lu, Haopeng, Wang, Shanshe, Zhang, Xinfeng, Gao, Wen

“…Most of the existing 3D human pose estimation approaches mainly focus on predicting 3D positional relationships between the root joint and other human joints…”
Get full text

Diffusion-Based Hypotheses Generation and Joint-Level Hypotheses Aggregation for 3D Human Pose Estimation by Shan, Wenkang, Zhang, Yuhuai, Zhang, Xinfeng, Wang, Shanshe, Zhou, Xilong, Ma, Siwei, Gao, Wen

“…To combine the advantages of deterministic and probabilistic 3D human pose estimation methods, we decompose pose estimation into two processes: hypotheses…”
Get full text

LFCAVE: Interactive 3D Space with Multiple Light Field Displays by Lu, Haopeng, Shan, Wenkang, Zhang, Yuhuai, Song, Li, Zhang, Xinfeng, Ma, Siwei, Zhang, Liuxin, Gao, Wen

“…We introduce LFCAVE, an interactive 3D display system comprised of display and interaction modules. In the display aspect, we have developed a multi-screen…”
Get full text

Real-Time Human Motion Transfer System for Holographic Displays by Shan, Wenkang, Lu, Haopeng, Jia, Chuanmin, Zhang, Xinfeng, Ma, Siwei, Wu, Yaqiang, Gao, Wen

“…This paper presents a human motion transfer system designed for holographic displays. It utilizes a single RGB camera to capture real-time human movement data…”
Get full text

Real-Time Interaction with Animated Human Figures in Chinese Ancient Paintings by Wei, Yifan, Shan, Wenkang, Zhang, Qi, Zhang, Liuxin, Zhang, Jian, Ma, Siwei

“…To promote the conservation and inheritance of Chinese ancient paintings, we propose an intelligent interaction system that animates ancient figures for…”
Get full text

Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation by Shan, Wenkang, Liu, Zhenhua, Zhang, Xinfeng, Wang, Zhao, Han, Kai, Wang, Shanshe, Ma, Siwei, Gao, Wen

“…In this paper, a novel Diffusion-based 3D Pose estimation (D3DP) method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) is proposed for…”
Get full text

P-STMO: Pre-Trained Spatial Temporal Many-to-One Model for 3D Human Pose Estimation by Shan, Wenkang, Liu, Zhenhua, Zhang, Xinfeng, Wang, Shanshe, Ma, Siwei, Gao, Wen

“…This paper introduces a novel Pre-trained Spatial Temporal Many-to-One (P-STMO) model for 2D-to-3D human pose estimation task. To reduce the difficulty of…”
Get full text