Appearance Models in Computer Graphics and Vision

COMS 6998-03, Fall 2002, Prof. Ravi Ramamoorthi Wednesday, 6:40-8:30, 833 Mudd


Artists and scientists have long been fascinated by understanding and modeling the appearance of everyday materials, ranging from human faces and clothing to natural materials like leaves, sand, and the sky. Within computer graphics, creating realistic images requires simulating and modeling many different materials. Within computer vision, understanding the world around us requires an understanding of the nature of effects related to illumination, reflectance and texture. In this course, we consider the computational aspects of appearance measurement, modeling, simulation, and analysis. Topics include reflectance models, acquisition of material models from real scenes, image-based modeling and rendering methods, interactive rendering with complex appearance models, and analysis techniques including low-dimensional lighting models, factored representations and signal-processing. Below are some example images and computer renderings corresponding to the types of appearance we will be discussing.


This is an advanced course concentrating on current research topics in computer graphics and vision. It is targetted towards students with a knowledge of and interest in computer graphics and/or computer vision (at the level of 4160 and/or 4731)

Course Format and Requirements

The course will consist of lectures on the relevant topics by the instructor, student presentations of papers covering current research in the area, and student projects. A syllabus/schedule is noted below. The grading will be 30% for paper presentations, 60% for the project, and 10% for class participation. A project is not required for students taking the course pass/fail. Auditors, who simply want to sit in on the course are also welcome; however, we prefer if you sign up for the course pass/fail instead [this just involves doing one or two paper presentations, depending on the number of students in the course].

Students taking the course for a letter grade are required to do a project [this may be in groups of 2-3], give a presentation in class regarding their results, and also submit a final written report. Wide flexibility is available with respect to project topics, provided they relate to the subject matter of the course. Some ideas are listed below. You can also implement an algorithm from any of the papers in the reading material. The best projects will go beyond the published work in some way, such as trying out an alternative or better approach or trying to develop some variant or more general version of the technique.

As a potentially easier alternative to the project, we will also accept a well-written summary or tutorial, covering 3 or 4 papers. The best summaries will point out links between the papers not noticed by the original authors and suggest improvements or directions for future research. However, this option is recommended only as a last resort and will generally receive a lower score; we prefer that you do a good project (which may involve understanding a few papers in any case).


Topics to be covered include



The tentative course schedule is as follows. This will likely change as the semester progresses, and the number of paper presentations may be reduced if the number of students is small.

Sep. 4: Sep. 11: Sep. 18: Sep. 25: Oct 2: Oct. 9: Oct. 16: Oct. 23: Oct. 30: Nov. 6: Nov. 13: Nov. 20: Nov 27: Dec 4:
Ravi Ramamoorthi
Last modified: Wed Nov 20 20:57:01 Pacific Standard Time 2002