Chengbiao Deng

About

Dr. Chengbiao Deng is a leading researcher in computer vision and robotics, with a primary focus on 6DoF (six degrees of freedom) object pose estimation. His work addresses a critical challenge in augmented reality and robotic manipulation: enabling machines to accurately determine an object’s position and orientation from a single image. Deng’s most cited paper, "Learning 6DoF Object Poses from Synthetic Single Channel Images" (2018, 32 citations), pioneered the use of deep neural networks trained exclusively on synthetic data to achieve robust pose estimation. This approach significantly reduces the need for labor-intensive real-world annotation, making it highly scalable for practical applications. By demonstrating that models can generalize from synthetic to real environments, Deng’s contributions have advanced the deployment of vision systems in AR and robotics. His research is notable for bridging the gap between simulation and reality, a key hurdle in embodied AI. With a growing citation impact, Deng’s work continues to inspire new methods for efficient, data-driven pose estimation, solidifying his reputation as an innovator in the field.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning 6DoF Object Poses from Synthetic Single Channel Images

   32 citations · 2018

Key Collaborators

Contact & Links