Chen-Hsuan Lin

Title: Innovations of Chen-Hsuan Lin

Introduction

Chen-Hsuan Lin is an accomplished inventor based in Pittsburgh, PA (US). He has made significant contributions to the field of image processing and 3D object reconstruction. With a total of 4 patents to his name, Lin's work is at the forefront of technological advancements.

Latest Patents

One of Lin's latest patents is titled "Image composites using a generative neural network." This patent describes an image composite system that utilizes a generative adversarial network to create realistic composite images. The system trains a geometric prediction neural network using an adversarial discrimination neural network to learn warp parameters. These parameters ensure correct geometric alignment of foreground objects with background images, allowing for natural blending when composited together.

Another notable patent is "3D object reconstruction using photometric mesh representation." This patent outlines techniques for reconstructing 3D objects through photometric mesh representations. A decoder is pretrained to transform points sampled from 2D patches of representative objects into 3D polygonal meshes. The process involves feeding an image frame into an encoder to obtain an initial latent code vector, followed by rendering a polygonal mesh at various viewpoints. The mesh is optimized by creating a virtual viewpoint and rasterizing to obtain a depth map, ensuring accurate alignment of 3D mesh projections.

Career Highlights

Chen-Hsuan Lin is currently employed at Adobe, Inc., where he continues to innovate and develop cutting-edge technologies. His work has garnered attention in the tech community, and he is recognized for his expertise in neural networks and image processing.

Collaborations

Lin collaborates with talented individuals in his field, including Elya Shechtman and Oliver Wang. These partnerships enhance the creative process and contribute to the success of their projects.

Conclusion

Chen-Hsuan Lin's contributions to the fields of image processing and 3D reconstruction are noteworthy. His innovative patents reflect his commitment to advancing technology and improving the way we interact with digital images.