Gengshan Yang

Title: Gengshan Yang: Innovator in 3D Shape Reconstruction

Introduction

Gengshan Yang is a notable inventor based in Pittsburgh, PA (US). He has made significant contributions to the field of computer vision and 3D modeling. His innovative work focuses on the reconstruction of articulated shapes from imagery, which has applications in various industries.

Latest Patents

Gengshan Yang holds a patent titled "Learning articulated shape reconstruction from imagery." This patent describes a computing system and method that can render a 3D shape from one or more images. The disclosed pipeline, known as LASR, is capable of reconstructing both rigid and non-rigid 3D shapes. It automatically decomposes non-rigidly deforming shapes into rigid motions near rigid bones. The pipeline employs an analysis-by-synthesis strategy and forward-renders silhouette, optical flow, and color images, which are compared against video observations to adjust the model's internal parameters. By inverting the rendering pipeline and incorporating optical flow, the system can recover a mesh of a 3D model from user-input images. Gengshan Yang has 1 patent to his name.

Career Highlights

Gengshan Yang is currently employed at Google Inc., where he continues to push the boundaries of technology and innovation. His work has garnered attention for its potential to enhance the accuracy and efficiency of 3D shape reconstruction.

Collaborations

Gengshan Yang has collaborated with talented individuals such as Deqing Sun and Varun Jampani. These collaborations have contributed to the advancement of his research and the development of innovative solutions in the field.

Conclusion

Gengshan Yang is a pioneering inventor whose work in 3D shape reconstruction is shaping the future of computer vision technology. His contributions are paving the way for new advancements in the industry.