3DGS Academy

Browse products

3D Gaussian Splatting from Scratch — PyTorch Only

Learn to build a full 3D Gaussian Splatting (3DGS) pipeline entirely in Python and PyTorch — no CUDA, no external libraries. This course walks you through every step of modern neural rendering: parsing COLMAP outputs, implementing 3D Gaussian primitives, creating a trainable radiance model, coding the optimization loop, and building a real-time differentiable renderer for photorealistic results. Ideal for researchers, graduate students, and developers who want a clean, modular PyTorch implementation and a deep understanding of 3DGS without C++ or CUDA. After 7k training iterations, your metrics will match those reported in the original paper. By the end, you’ll have a complete working implementation ready for extension and research use.

CourseBy Maxime Vandegar

Learn more

Introduction to Diffusion Models

This course explores Diffusion Models, a powerful technique in machine learning and generative AI. It covers the theory behind these models, starting from foundational research papers and advancing to practical applications. You'll learn to implement Diffusion Models from scratch using PyTorch, with a focus on image generation, inpainting (filling in missing parts of images), and animations. The course provides hands-on coding examples, making it ideal for anyone interested in deepening their understanding of generative models and their use in creative AI projects.

CourseBy Maxime Vandegar

Learn more

Introduction to Machine Learning

Learn machine learning from first principles by implementing core algorithms from scratch. You’ll understand training, evaluation, and optimization deeply—then build up to neural networks with clarity and rigor.

CourseBy Maxime Vandegar

Learn more