Stanford AI Course Map 中文 GitHub ↗
← Back to the course map
Stanford · 2026—27 CS 448I Vision, Graphics & Generative Models ★★★★☆

Core course · Vision, Graphics & Generative Models

Computational Imaging (EE 367)

中文:计算成像

Computational imaging: from convolution/denoising to inverse problems, wave optics, and end-to-end optics-algorithm co-design.

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

Offered in Winter 2026–27; no stable course-site link found.

3 units Winter 2027 Letter or Credit/No Credit ★★★★☆
ImagingInverse problemsOpticsCV

Course positioning

CS 448I (EE 367) is taught by Gordon Wetzstein and is a core course in computational photography/imaging. It combines classical image processing, convex optimization, and modern AI, covering denoising, deconvolution, single-pixel imaging, ToF, wave optics, and end-to-end joint optimization of optics and algorithms.

What it covers

  1. Image processing basics: convolution, filtering, denoising
  2. Inverse problems: deconvolution, regularization, proximal gradient
  3. CNNs for imaging: image restoration, learned priors
  4. Single-pixel imaging: coded apertures, compressed sensing
  5. Wave optics: diffraction, holography, phase retrieval
  6. ToF imaging: depth measurement, multipath
  7. End-to-end optimization: joint optics + algorithm design
  8. Project

Prerequisites

Signal/image processing/optimization basics; Python programming.

Assessment & workload

Assignments plus a term project, emphasizing implementation. Check the current syllabus for details.

Who it's for

Computational photography, imaging systems, AR/VR, and microscopy/medical imaging.

Study advice

Brush up on linear algebra and signals & systems first. Pair with EE 367.

Related courses

Official course description

Digital photography and basic image processing, convolutional neural networks for image processing, denoising, deconvolution, single pixel imaging, inverse problems in imaging, proximal gradient methods, introduction to wave optics, time-of-flight imaging, end-to-end optimization of optics and imaging processing. Emphasis is on applied image processing and solving inverse problems using classic algorithms, formal optimization, and modern artificial intelligence techniques. Students learn to apply material by implementing and investigating image processing algorithms in Python. Term project.