Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 CS 468 Vision, Graphics & Generative Models ★★★★☆

Core course · Vision, Graphics & Generative Models

Topics in Geometric Computing - 3D and 4D Foundation Models

中文:几何计算专题:3D/4D 基础模型

A special-topics course in geometric computing, recently focused on 3D/4D foundation models.

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

Not offered in the 2026–27 ExploreCourses listing.

3 units Not scheduled in 2026–27 Letter or Credit/No Credit ★★★★☆
Geometry3DGraphicsTopics

Course positioning

CS 468 is a topics course whose content changes each offering; past years covered geometric matching, surface reconstruction, collision detection, computational topology, computer differential geometry, data-driven shape analysis, and non-Euclidean machine learning. Recent offerings shifted to 3D/4D foundation models; it suits graduate students with a geometry/graphics background.

What it covers

  1. Geometric matching: rigid/non-rigid registration
  2. Surface reconstruction: point clouds to meshes, implicit representations
  3. Collision detection: spatial data structures
  4. Computational topology: persistent homology, topological data analysis
  5. Differential geometry: discrete surfaces, curvature
  6. 3D/4D foundation models: multimodal 3D representations, dynamic scenes
  7. Paper reading and project

Prerequisites

Graphics/geometry/vision background; programming and mathematical maturity.

Assessment & workload

Paper discussion plus a project/reproduction. Check the current syllabus for details.

Who it's for

Graduate students in 3D vision, graphics, or geometry processing; people interested in 3D foundation models.

Study advice

Take CS 148/CS 231A first. Topics change every year; read the current syllabus before enrolling.

Related courses

Official course description

Contents of this course vary with each offering. Past offerings have included geometric matching, surface reconstruction, collision detection, computational topology, differential geometry for computer scientists, computational symmetry and regularity, data-driven shape analysis, and non-Euclidean methods in machine learning.