CS295 Realistic Image Synthesis

University of California @ Irvine, Spring 2019

T/Th 3:30pm, DBH 1423

Instructor: Shuang Zhao (office hour: by appointment)

Course Information

Contents: This course offers an introduction to physics-based rendering at the graduate level. Starting from the fundamentals of light transport we will look at formulations of the Rendering Equation (RE) and the Radiative Transfer Equation (RTE), as well as a series of Monte Carlo methods for solving these equations to make pictures. We will look at light reflection from surfaces and scattering in volumes, illumination from luminaires and environments, and diffusion models for translucent materials. We will build working implementations of many of the algorithms we study, and learn how to make sure they are actually working correctly. It is fun to watch integrals and probability distributions transform into photographs of synthetic worlds.

Prerequisites: It is recommended (but not required) to have taken an introductory level course in computer graphics (e.g., CS112). We will rely on calculus, linear algebra and use basic concepts of algorithms and data structures. Students are expected to be familiar with the C++ programming language that is used in the programming assignments.

Announcements

• Apr 1: Course website is up!
• Apr 16: Homework 1 is out and will be due in one week.

Schedule

, PA1 out

date		topic	reading	assignment
2	Apr	intro
4	Apr	radiometry & BRDFs	Preisendorfer 1976, Sec. 1.1 Montes & Ureña 2012
9	Apr	direct illumination & Monte Carlo integration I
11	Apr	Monte Carlo integration II & sampling from PDFs
16	Apr	sampling from PDFs II	Press et al. 1992, Ch. 7	HW1 out
18	Apr	rendering equation & Monte Carlo path tracing I	Kajiya 1986
23	Apr	Monte Carlo path tracing II	Veach 1997, Ch. 9	HW1 due
25	Apr	Monte Carlo path tracing III & operator formulation of light transport	Veach 1997, Ch. 4
30	Apr	operator formulation of light transport II
2	May	path integral formulation	Veach 1997, Ch. 8
7	May	no class
9	May	path integral formulation II & light path expressions	Heckbert 1990	PA1, PA2 out
14	May	no class
16	May	bidirectional path tracing I	Veach 1997, Ch. 10
21	May	bidirectional path tracing II	Veach 1997, Ch. 10	PA1 due
23	May	refraction & BSDFs	Veach 1997, Ch. 5.2
28	May	student presentation 1
30	May	student presentation 2
4	Jun	radiative transfer & volume path tracing	Marschner 2015	PA2 due
6	Jun	Metropolis light transport	Veach 1997, Ch. 11

Readings

[Heckbert 1990]	Adaptive Radiosity Textures for Bidirectional Ray Tracing
[Kajiya 1986]	The Rendering Equation
[Marschner 2015]	Volume Light Transport (Course Notes)
[Montes & Ureña 2012]	An Overview of BRDF Models
[Preisendorfer 1976]	Hydrologic Optics
[Press et al. 1992]	Numerical Recipes in C (Second Edition)
[Veach 1997]	Robust Monte Carlo Methods for Light Transport Simulation

Extra Readings

[Debevec et al. 2000]	Acquiring the Reflectance Field of a Human Face
[Keller 1997]	Instant Radiosity
[Matusik et al. 2003]	A Data-Driven Reflectance Model
[Ngan et al. 2005]	Experimental Analysis of BRDF Models
[Lehtinen et al. 2011]	Temporal Light Field Reconstruction for Rendering Distribution Effects
[Lehtinen et al. 2012]	Reconstructing the Indirect Light Field for Global Illumination
[Walter et al. 2005]	Lightcuts: a Scalable Approach to Illumination
[Walter et al. 2007]	Microfacet Models for Refraction through Rough Surfaces

Assignments

Course Policies

Questions, help, discussion: The instructor is available to answer questions, advise on projects, or just to discuss interesting topics related to the class at office hours and by appointment as needed. For electronic communication we are using Piazza (handy link also at the top of this page).

Academic integrity: We assume the work you hand in is your own, and the results you hand in are generated by your program. You're welcome to read whatever you want to learn what you need to do the work, but we do expect you to build your own implementations of the methods we are studying. If you're ever in doubt, just include a citation in your code or report indicating where some idea came from, whether it be a classmate, a web site, another piece of software, or anything—this always maintains your honesty, whether the source was used in a good way or not. The principle is that an assignment is an academic document, like a journal article. When you turn it in, you are claiming that everything in it is your original idea (or is original to you and your partner, if you're handing in as a pair) unless you cite a source for it.

School can be stressful, and your coursework and other factors can put you under a lot of pressure, but that is never a reason for dishonesty. If you feel you can't complete the work on your own, come talk to the professor, or your advisor, and we can help you figure out what to do. Think before you hand in!

Clear-cut cases of dishonesty will result in failing the course.

For more information see UCI's Policy on Academic Honesty.

Collaboration: You are welcome (encouraged, even) to discuss projects among yourselves in general terms. But when it comes to writing up the homeworks or implementing the projects, you need to be working alone (or only with your partner if you are doing a project as a pair). In particular, it's never OK for you to see another student's homework writeup or another team's program code, and certainly never OK to copy parts of one person's or team's writeup, code, or results into another's, even if the general solution was worked out together.