Ta-Ying Cheng

Title: Ta-Ying Cheng: Innovator in Image Processing Technologies

Introduction

Ta-Ying Cheng is an inventor based in Oxford, GB. He is known for his contributions to the field of image processing, particularly in the development of methods for generating synthetic images and extracting 3D shapes from large-scale datasets. Although he currently holds no granted patents, his innovative ideas are reflected in his latest patent applications.

Latest Patent Applications

Ta-Ying Cheng's latest patent applications include:

1. **LEARNING CONTINUOUS CONTROL FOR 3D-AWARE IMAGE GENERATION ON TEXT-TO-IMAGE DIFFUSION MODELS** - This application describes a method, apparatus, non-transitory computer readable medium, and system for image processing. It involves obtaining a text prompt that describes an element and an attribute value for a continuous attribute of the element. The process includes embedding the text prompt to obtain a text embedding in a text embedding space, embedding the attribute value to obtain an attribute embedding, and generating a synthetic image based on these embeddings. The synthetic image depicts the continuous attribute of the element based on the attribute value.

2. **EXTRACTING 3D SHAPES FROM LARGE-SCALE UNANNOTATED IMAGE DATASETS** - This application outlines systems and methods for extracting 3D shapes from unstructured and unannotated datasets. It describes obtaining a first image and a second image, where the first image depicts an object and the second image includes a corresponding object of the same category. The method involves generating image features for portions of both images, identifying keypoint correspondences, and generating a 3D model of the object based on these correspondences.

Conclusion

Ta-Ying Cheng is an innovative inventor whose work in image processing holds promise for advancements in technology. His latest patent applications reflect his commitment to developing cutting-edge solutions in the field.