Cardioid Caustics Generation with Conditional Diffusion Models

Loading...
Thumbnail Image
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Despite the latest advances in generative neural techniques for producing photorealistic images, they lack generation of multi-bounce, high-frequency lighting effect like caustics. In this work, we tackle the problem of generating cardioid-shaped reflective caustics using diffusion-based generative models. We approach this problem as conditional image generation using a diffusion-based model conditioned with multiple images of geometric, material and illumination information as well as light property. We introduce a framework to fine-tune a pre-trained diffusion model and present results with visually plausible caustics.
Description

CCS Concepts: Computing methodologies → Artificial intelligence; Neural networks; Image-based rendering

        
@inproceedings{
10.2312:egs.20251030
, booktitle = {
Eurographics 2025 - Short Papers
}, editor = {
Ceylan, Duygu
and
Li, Tzu-Mao
}, title = {{
Cardioid Caustics Generation with Conditional Diffusion Models
}}, author = {
Uss, Wojciech
and
Kaliński, Wojciech
and
Kuznetsov, Alexandr
and
Anand, Harish
and
Kim, Sungye
}, year = {
2025
}, publisher = {
The Eurographics Association
}, ISSN = {
1017-4656
}, ISBN = {
978-3-03868-268-4
}, DOI = {
10.2312/egs.20251030
} }
Citation