Qiang Peng — accepted AI-conference papers

2024

PostureHMR: Posture Transformation for 3D Human Mesh Recovery

Yu-Pei Song, Xiao Wu, Zhaoquan Yuan, Jian-Jun Qiao, Qiang Peng

CVPR 2024poster

Human Mesh Recovery (HMR) aims to estimate the 3D human body from 2D images which is a challenging task due to inherent ambiguities in translating 2D observations to 3D space. A novel approach called PostureHMR is proposed to leverage a multi-step diffusion-style process which converts this task int…

Cited by 3 Source ↗PDF ↗Scholar ↗

2019

Generative Adversarial Networks Based Error Concealment for Low Resolution Video

Chongyang Xiang, Jiajun Xu, Chuan Yan, Qiang Peng, Xiao Wu

ICASSP 2019accepted

In this paper, a novel deep generative model-based approach for video error concealment is proposed. Our method is comprised of completion network and two critics. The frame completion network is trained to fool the both the local and global critics, which requires completion network to conceal fram…

Cited by 0 Source ↗Scholar ↗