CS Talk: Zahra Montazeri

Speaker: Zahra Montazeri

Date: Tuesday, November 15th, 2022

Time: 3:30 - 4:30 pm

Location: HFH 1132

Host: Linqi Yan

Title: Realistic Modeling and Rendering of Fabrics 

Abstract:

Modeling cloth appearance, an active research topic in computer graphics for decades generally, boils down to representing the geometry and optics of a fabric. Existing models can 

be broadly classified into two categories. Surface-based models depict cloth geometry using smooth 2D sheets and optics using specialized reflectance models. Micro-appearance models, on the other hand, express cloth geometry at the microscale down to individual micron-diameter fibers and optics by utilizing volumetric or fiber-based light scattering models. 

In practice, both categories have their own advantages and disadvantages. The surface-based models are typically lightweight, easy to edit, and can faithfully reproduce the appearance of fabric at the macro-scale. Thus, they have been widely used in the computer graphics industry. However, these models lack the fine-grained details that are crucial for cloth rendering under close-up views. The micro-appearance models, in contrast, are capable of generating renderings with remarkably high fidelity and details. Unfortunately, as these models are highly data-intensive and usually difficult to manipulate, their practical use has been quite limited. 

In this talk, we present a family of new techniques to efficiently build and render fabric models with fiber-level details. Our first contribution tackles the challenge of an extension of the micro-structure models by supporting fabric mechanics. Our second contribution focuses 

on a practical appearance model for woven fabrics that represents the cloth at the ply level and offers an interactive rendering process. Lastly, our third contribution aims for extending this practical model for knitted fabrics. We also believe the techniques discussed in this talk can inspire insights for other materials beyond fabrics such as hair and fur.

Bio: 

Zahra is an Assistant Professor (lecturer) at the University of Manchester in the department of Computer Science and a part-time consultant at Disney Research. Her field is physics-based computer graphics with a focus on photorealistic rendering and appearance modeling for complex materials such as cloth, hair and fur. Before joining academia, she was an R&D at Industrial Light and Magic (ILM) and during her studies, she worked at Pixar Animation Studios, DreamWorks Animation, and two years at Luxion (makers of KeyShot). She holds a PhD in Computer Science from the University of California, Irvine, advised by Dr Shuang Zhao and worked under the supervision of Prof. Henrik Jensen. She received her M.Sc. in Computer Science from the University of California, Irvine in 2017 and her B.Sc. in Computer Engineering from Sharif University of Technology in 2015, Iran.