Generative AI for 3D Modeling

Working at the meeting point of generative AI and visual creation, Dr. Alfred Ang builds tools that turn plain descriptions into images, scenes and interactive graphics. Dr. Ang is a full-stack AI developer, Agentic AI solution architect and corporate trainer, and serves as CTO of Tertiary Infotech Academy Pte Ltd, the Singapore training organisation behind Tertiary Courses, delivering solutions end-to-end from front end and back end to databases, cloud deployment and native mobile apps. More than 300 public repositories on GitHub capture that range. The most relevant to this course is a browser-based WebXR playground for generating and reviewing AR and VR scenes from vibe prompts, where a short description becomes a three-dimensional environment that can be explored and refined. Dr. Ang also built a logo generator that produces design options from a text brief using Gemini or OpenAI image models, an offline GPU-accelerated fractal art generator for iPhone and iPad with an OpenGL-based Android counterpart, and a Procreate-style sketching studio with layers, symmetry and pressure-sensitive brushes on iOS and Android. A video creation tool that turns any topic into a narrated, animated video completes a portfolio centred on prompt-driven visual work, where the creative brief comes from a person and the repetitive generation is handled by AI. Building these tools has given Dr. Ang a practical understanding of how prompt wording, reference material and iteration shape generated output, and of the review steps needed before AI-created visuals are good enough to share with clients, colleagues or a production team.

In Generative AI for 3D Modeling, Dr. Ang uses that experience to help product designers, engineers, architects, game and animation artists and makers adopt AI-assisted 3D workflows with confidence. The first topic covers generative AI for 3D design concepts and modelling, showing how text descriptions, reference images and sketches can be turned into initial 3D models in minutes, and how to write prompts that control form, proportion and style. The second topic turns to AI-assisted analysis, validation and refinement: inspecting generated meshes for problems, comparing variations, and iterating on details until a concept is fit for review. The final topic deals with optimisation, standards and production workflows, including cleaning up geometry, preparing models for rendering, real-time use or fabrication, and exporting to the formats downstream teams need. Drawing on the iterate-and-review loop built into the WebXR playground and the image tools in the portfolio, Dr. Ang stresses that AI accelerates the early and repetitive stages while human judgement decides what is good enough to ship. Sessions combine live demonstrations with guided practice, and participants are encouraged to bring their own design challenges so they leave with models and a repeatable workflow they can apply at work. Participants also discuss practical considerations such as intellectual property in AI-generated assets, keeping a clear record of prompts and versions, and communicating with engineers or clients about what an AI-assisted concept can and cannot yet show, so that adoption fits smoothly into existing design processes. Learners can explore Dr. Ang's visual AI projects at https://github.com/alfredang.