Abstract: Human beings can easily categorize three-dimensional (3D) objects with similar shapes and functions into a set of “visual concepts” and learn “visual knowledge” of the surrounding 3D real world (Pan, 2019). Developing efficient methods to learn the computational representation of the visual concept and the visual knowledge is a critical task in artificial intelligence (Pan, 2021a). A crucial step to this end is to learn the shape space spanned by all 3D objects that belong to one visual concept. In this paper, we present the key technical challenges and recent research progress in 3D shape space learning and discuss the open problems and research opportunities in this area.

Key words:

Please provide your name, email address and a comment

Your Name: Affili: E-Mail Address:

Comment (Please comment in English):


Verification Code(click to change a pic):