Physics-based Rendering Course ID 15868 Description This course is an introduction to physics-based rendering at the advanced undergraduate and introductory graduate level. During the course, we will cover fundamentals of light transport, including topics such as the rendering and radiative transfer equations, light transport operators, path integral formulations, and approximations such as diffusion and single scattering. Additionally, we will discuss state-of-the-art models for illumination, surface and volumetric scattering, and sensors. Finally, we will use these theoretical foundations to develop Monte Carlo algorithms and sampling techniques for efficiently simulating physically-accurate images. Towards the end of the course, we will look at advanced topics such as rendering wave optics, neural rendering, and differentiable rendering. The course has a strong programming component, in the form of assignments through which students will develop their own working implementation of a physics-based renderer, including support for a variety of rendering algorithms, materials, illumination sources, and sensors. The course also emphasizes theoretical aspects of physics-based rendering, through weekly take-home quizzes. Lastly, the course includes a final project, during which students will select and implement some advanced rendering technique, and use their implementation to produce an image that is both technically and artistically compelling. The course will conclude with a rendering competition, where students submit their rendered images to win prizes. Key Topics This course is an introduction to physics-based rendering at the advanced undergraduate and introductory graduate level. During the course, we will cover fundamentals of light transport, including topics such as the rendering and radiative transfer equations, light transport operators, path integral formulations, and approximations such as diffusion and single scattering. Additionally, we will discuss state-of-the-art models for illumination, surface and volumetric scattering, and sensors. Finally, we will use these theoretical foundations to develop Monte Carlo algorithms and sampling techniques for efficiently simulating physically-accurate images. Towards the end of the course, we will look at advanced topics such as rendering wave optics, neural rendering, and differentiable rendering. Required Background Knowledge Background in multivariable calculus, probability, programming. must have a passing grade in 16-385, 16-720, 15-462/15-662, OR 15-463/15-663/15-862 Course Relevance The course should be relevant to junior and senior undergraduate, MS, and doctoral students with interest in any of the following: computer science, computer graphics, computer vision, optics, applied physics, imaging, numerical computing, Monte Carlo computing. Course Goals Students should become fluent in the mathematics of light transport, Monte Carlo algorithms for light transport simulation, and engineering of rendering systems. Learning Resources All resources are available in the course website. Assessment Structure Four two-week programming assignments (50%). Ten take-home quizzes (25%). Final project and rendering competition (25%). Extra Time Commitment This course has an optional but important weekly recitation ("Review-Discussion") session on Wednesdays 3:30-5 pm. Course Link http://graphics.cs.cmu.edu/courses/15-468/
