Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 CS 348I Vision, Graphics & Generative Models ★★★★☆

Core course · Vision, Graphics & Generative Models

Computer Graphics in the Era of AI

中文:AI 时代的计算机图形学

Computer graphics in the AI era: neural rendering, differentiable rendering, materials/textures, animation, and physics simulation.

Draft translation: official facts are checked; wording may change after native review.

Not offered in the 2026–27 ExploreCourses listing; no stable course-site link found.

3–4 units Not scheduled in 2026–27 Letter or Credit/No Credit ★★★★☆
GraphicsNeural rendering3DGeneration

Course positioning

CS 348I discusses how deep learning is changing four areas of graphics: rendering, geometry, animation, and imaging. For each problem it presents the classical solution first, then SOTA learned methods, and critically evaluates results and impact — a good fit for graphics + AI.

What it covers

  1. Differentiable/neural rendering: NeRF, Gaussian Splatting, neural rendering
  2. Materials and lighting: BRDF estimation, inverse rendering
  3. Textures and images: texture synthesis, denoising, super-resolution, shading
  4. Geometry: neural implicits, procedural modeling
  5. View synthesis: novel-view generation, 3D reconstruction
  6. Animation: motion synthesis, differentiable physics, RL
  7. Project

Prerequisites

CS 148; CS 231N recommended.

Assessment & workload

Programming assignments plus a project. Check the current syllabus for details.

Who it's for

Graphics, rendering, 3D generation, and film/game technology.

Study advice

Brush up on graphics fundamentals (ray tracing, BRDF, rendering equation) first. Pair with CS 348N/CS 468.

Related courses

Official course description

This course introduces deep learning methods and AI technologies applied to four main areas of Computer Graphics: rendering, geometry, animation, and imaging. We will study a wide range of problems on content creation for images, shapes, and animations, recently advanced by deep learning techniques. For each problem, we will understand its conventional solutions, study the state-of-the-art learning-based approaches, and critically evaluate their results as well as the impacts to researchers and practitioners in Computer Graphics. The topics include differentiable rendering/neural rendering, BRDF estimation, texture synthesis, denoising, procedural modeling, view synthesis, colorization, style transfer, motion synthesis, differentiable physics simulation, and reinforcement learning. Through programming projects and homework, students who successfully complete this course will be able to use neural rendering algorithms for image manipulation, apply neural procedural modeling for shape and scene synthesis, exploit data-driven methods for simulating physical phenomena, and implement policy learning algorithms for creating character animation. Recommended Prerequisites: CS148, CS231N