Stanford AI 课程地图 EN GitHub ↗
← 返回课程地图
Stanford · 2026—27 CS 348I 视觉、图形与生成 ★★★★☆

核心课程 · 视觉、图形与生成

AI 时代的计算机图形学

Computer Graphics in the Era of AI

AI 时代的图形学:神经渲染、可微渲染、材质/纹理、动画、物理仿真。

3–4 学分 2026–27 未排课 Letter or Credit/No Credit ★★★★☆
图形神经渲染3D生成

2026-27 学年未在 ExploreCourses 排课;官网暂未找到稳定链接。

课程定位

CS 348I 讨论深度学习如何改变图形学的四大领域:渲染、几何、动画和成像。课程对每个问题先讲传统解法,再讲 SOTA 学习式方法,并批判性评估结果与影响,适合图形+AI 交叉方向。

主要内容

  1. 可微/神经渲染:NeRF、Gaussian Splatting、神经渲染
  2. 材质与光照:BRDF 估计、逆渲染
  3. 纹理与图像:纹理合成、去噪、超分、着色
  4. 几何:神经隐式、程序化建模
  5. 视角合成:新视角生成、3D 重建
  6. 动画:动作合成、可微物理、RL
  7. 项目

先修

CS 148;CS 231N 推荐。

考核与工作量

编程作业 + 项目。具体以当季官网为准。

适合谁

图形学、渲染、3D 生成、影视/游戏技术方向。

学习建议

先补图形学基础(光线追踪、BRDF、渲染方程)。配合 CS 348N/CS 468。

相关课程

官方课程描述(英文原文)

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