Integrating artificial intelligence (AI) into computer-aided design (CAD) has shown the potential to transform design and manufacturing processes, enabling more efficient, intuitive, and intelligent workflows. In recent years, the application of AI to 3D CAD model generation tasks has gradually emerged. To better enable researchers to understand the current research status of the AI-based CAD generation field and to inspire them to conduct further research, this survey explores the role of AI in 3D CAD model generation tasks that utilize various representations and conditions, ranging from traditional machine learning to LLM-based approaches. Additionally, AI applications in other extended CAD areas are also touched upon in the survey. Finally, we analyze current progress, identify challenges and limitations faced by this field, and propose possible directions for future work.

A geometric mapping establishes a correspondence between two domains. Since no real object has zero or negative volume, such a mapping is required to be inversion-free. Computing inversion-free mappings is a fundamental task in numerous computer graphics and geometric processing applications, such as deformation, texture mapping, mesh generation, and others. This task is usually formulated as a non-convex, nonlinear, constrained optimization problem. Various methods have been developed to solve this optimization problem. As well as being inversion-free, different applications have various further requirements. We expand the discussion in two directions to (i) problems imposing specific constraints and (ii) combinatorial problems. This report provides a systematic overview of inversion-free mapping construction, a detailed discussion of the construction methods, including their strengths and weaknesses, and a description of open problems in this research field.

3D shape editing is widely used in a range of applications such as movie production, computer games and computer aided design. It is also a popular research topic in computer graphics and computer vision. In past decades, researchers have developed a series of editing methods to make the editing process faster, more robust, and more reliable. Traditionally, the deformed shape is determined by the optimal transformation and weights for an energy formulation. With increasing availability of 3D shapes on the Internet, data-driven methods were proposed to improve the editing results. More recently as the deep neural networks became popular, many deep learning based editing methods have been developed in this field, which are naturally data-driven. We mainly survey recent research studies from the geometric viewpoint to those emerging neural deformation techniques and categorize them into organic shape editing methods and man-made model editing methods. Both traditional methods and recent neural network based methods are reviewed.