Pengxu Wei

About

Pengxu Wei is a leading researcher in computer vision and machine learning, with a primary focus on 3D human pose estimation and self-supervised learning. His most impactful work, "3D Human Pose Machines with Self-supervised Learning" (2019), has garnered over 100 citations, addressing critical challenges in recovering 3D human poses from images—a task complicated by diverse appearances, occlusions, and geometric ambiguities. This contribution is pivotal for advancing applications in robotics, augmented reality, and human-computer interaction. By integrating self-supervised techniques, Wei’s research reduces reliance on costly annotated data, making 3D pose estimation more scalable and robust. His work stands out for its practical relevance, bridging the gap between theoretical models and real-world deployment. Beyond this flagship paper, Wei’s broader portfolio explores innovative approaches to visual understanding, earning him recognition as a rising figure in the field. His achievements underscore a commitment to solving fundamental problems in computer vision, with potential impacts across autonomous systems and interactive technologies. For students and researchers, Wei’s research exemplifies how self-supervised learning can unlock new frontiers in 3D human analysis.

Research Focus

Key Achievements

Top Papers

1. 1
   3D Human Pose Machines with Self-supervised Learning

   100 citations · 2019
2. 2
   3D Human Pose Machines with Self-supervised Learning

   2 citations · 2019

Key Collaborators

Contact & Links