Shaoting Zhang

University of North Carolina at Charlotte

Papers

Total Citations

178

H-Index

About

Shaoting Zhang is a leading researcher at the intersection of computer vision, graphics, and robotics, with a primary focus on multi-view generation and representation learning. His most impactful contribution is the development of **CR-GAN (Complete Representation GAN)**, a groundbreaking framework that addresses the fundamental challenge of generating realistic multi-view images from a single input. Zhang identified that conventional GANs often learn "incomplete" representations due to their single-pathway architecture, leading to inconsistent or distorted outputs. By introducing a dual-pathway design that enforces both reconstruction and generation, CR-GAN learns more complete and robust latent representations, significantly improving the quality and diversity of synthesized views. This work has garnered over 178 citations across its two key publications (2018), underscoring its influence in the field. Zhang’s research has broad applications in autonomous navigation, 3D modeling, and augmented reality, where reliable multi-view synthesis is critical. His contributions have been recognized through high-impact publications and ongoing collaborations with industry leaders, positioning him as a key innovator in generative models for visual computing.