Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 CS 231A Vision, Graphics & Generative Models ★★★★☆

Core course · Vision, Graphics & Generative Models

Computer Vision: From 3D Perception to 3D Reconstruction and Beyond

中文:计算机视觉:从 3D 感知到重建

Computer vision from camera models to 3D reconstruction: geometry first, deep learning second.

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

Not offered in the 2026–27 ExploreCourses listing.

3–4 units Not scheduled in 2026–27 Letter or Credit/No Credit ★★★★☆
CV3DGeometryReconstruction

Course positioning

CS 231A is the classic course on 3D vision and geometry, complementing CS 231N: 231N leans recognition and deep learning, while 231A leans cameras, projection, stereo, SfM, and 3D understanding. It is more mathematical and geometric, and suits people interested in AR/VR, robotics, and autonomous-driving perception.

What it covers

  1. Cameras and projection: pinhole model, intrinsics/extrinsics, distortion
  2. Image processing: filtering, edges, feature points
  3. Segmentation and clustering: classical and learned methods
  4. Stereo vision: epipolar geometry, depth estimation
  5. SfM and SLAM basics: structure from motion
  6. Recognition: objects, scenes, faces, actions
  7. Project: 3D reconstruction or a vision application

Prerequisites

Linear algebra; basic probability and statistics; programming.

Assessment & workload

Assignments plus a project, including geometric derivations and implementation. Check the current syllabus for details.

Who it's for

3D vision, robotics, AR/VR, and autonomous-driving perception; CV students who want geometry foundations.

Study advice

Take CS 231N first or concurrently. Derive epipolar geometry and bundle adjustment by hand.

Related courses

Official course description

(Formerly 223B) An introduction to the concepts and applications in computer vision. Topics include: cameras and projection models, low-level image processing methods such as filtering and edge detection; mid-level vision topics such as segmentation and clustering; shape reconstruction from stereo, as well as high-level vision tasks such as object recognition, scene recognition, face detection and human motion categorization. Prerequisites: linear algebra, basic probability and statistics.