Quality-Centric Single-Image Procedural Material Generation
Name
li-beichen-phd-eecs-2025-thesis.pdf
Description
Thesis PDF
Size
175.56 MB
Format
Adobe PDF
Checksum (MD5)
43d8eab5c6ce1c222ae890d2b527873b
Author(s)
Li, Beichen
Advisor(s)
Matusik, Wojciech
Date Issued
February 2025
Publisher
Massachusetts Institute of Technology
Abstract
Procedural materials, represented as functional node graphs, are ubiquitous in computer graphics for photorealistic material appearance design. They allow users to perform intuitive and precise editing to achieve desired visual appearances. However, even for experienced artists, creating a procedural material given an input image requires professional knowledge and significant effort. Current inverse procedural material modeling approaches enable the automatic generation of procedural materials from input images. However, the visual quality of the generated materials is fundamentally limited by insufficient high-quality training data from industry-standard procedural materials, reliance on token-space supervision without visual feedback, and the absence of approximation-free node parameter post-optimization. My thesis presents advanced dataset augmentation, model training, and parameter post-optimization algorithms to address these challenges, significantly improving the perceptual match between the generated procedural material and the input image. Furthermore, the methodologies can be applied to other inverse procedural graphics problems to expedite similar artistic creation processes.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright retained by author(s)
Persistent DSpace Link
