Cheng-Hao Kuo

Papers

Total Citations

H-Index

About

Cheng-Hao Kuo is a leading researcher at the intersection of computer vision and robotics, with a primary focus on 3D perception, object instance segmentation, and generative AI for robotic manipulation. His most impactful work, "SupeRGB-D: Zero-Shot Instance Segmentation in Cluttered Indoor Environments," addresses a critical challenge for indoor robots: detecting and segmenting every object in highly cluttered spaces without prior training data. This research, which has garnered over 13 citations, proposes a novel approach that overcomes the limitations of 3D sensing by leveraging deep learning to recognize objects that are often missed by traditional methods. Kuo’s contributions are vital for enabling robots to navigate and interact with complex, real-world environments. His more recent work, "Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors," pushes the boundaries of 3D object generation from a single unposed RGB image, a key capability for precise manipulation and scene understanding. By combining Gaussian splatting with hybrid diffusion priors, Kuo is advancing the field of robotic perception, making it possible for autonomous systems to reconstruct complete geometry and texture from minimal visual input. His research is essential for the next generation of dexterous, autonomous robots.