首页|Patent Application Titled 'Machine Learning Techniques For Direct Boundary Repre sentation Synthesis' Published Online (USPTO 20240289502)
Patent Application Titled 'Machine Learning Techniques For Direct Boundary Repre sentation Synthesis' Published Online (USPTO 20240289502)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
Reporters obtained the following quote from the background information supplied by the inventors: “ “Field of the Various Embodiments “Embodiments of the present disclosure relate generally to machine learning and computer-aided design and, more specifically, to machine learning techniques for generating representations of three-dimensional objects in boundary representat ion format. “Description of the Related Art “In the field of computer-aided design (CAD), boundary representation (B-rep) is a common format for representing three-dimensional (3D) shapes such as solid ob jects. In boundary representation, a solid object is defined by the limits of it s volume and represented as a collection of connected surface elements that defi ne the boundary between the object’s interior and exterior points. Boundary repr esentation synthesis refers to the automatic generation of a boundary representa tion of an object and is an enabling technology for design exploration, allowing automatic generation of a wide variety of 3D shape representations.
NETL
NSTL
