18892186. SINGLE IMAGE TO REALISTIC 3D OBJECT GENERATION VIA SEMI-SUPERVISED 2D AND 3D JOINT TRAINING (NVIDIA Corporation)
SINGLE IMAGE TO REALISTIC 3D OBJECT GENERATION VIA SEMI-SUPERVISED 2D AND 3D JOINT TRAINING
Organization Name
Inventor(s)
Morteza Mardani of Santa Clara CA US
Jiaming Song of San Carlos CA US
Sifei Liu of Santa Clara CA US
Arash Vahdat of San Mateo CA US
SINGLE IMAGE TO REALISTIC 3D OBJECT GENERATION VIA SEMI-SUPERVISED 2D AND 3D JOINT TRAINING
This abstract first appeared for US patent application 18892186 titled 'SINGLE IMAGE TO REALISTIC 3D OBJECT GENERATION VIA SEMI-SUPERVISED 2D AND 3D JOINT TRAINING
Original Abstract Submitted
Virtual reality and augmented reality bring increasing demand for 3D content creation. In an effort to automate the generation of 3D content, artificial intelligence-based processes have been developed. However, these processes are limited in terms of the quality of their output because they typically involve a model trained on limited 3D data thereby resulting in a model that does not generalize well to unseen objects, or a model trained on 2D data thereby resulting in a model that suffers from poor geometry due to ignorance of 3D information. The present disclosure jointly uses both 2D and 3D data to train a machine learning model to be able to generate 3D content from a single 2D image.