Cardioid Caustics Generation with Conditional Diffusion Models

Simple item page
dc.contributor.authorUss, Wojciechen_US
dc.contributor.authorKaliński, Wojciechen_US
dc.contributor.authorKuznetsov, Alexandren_US
dc.contributor.authorAnand, Harishen_US
dc.contributor.authorKim, Sungyeen_US
dc.contributor.editorCeylan, Duyguen_US
dc.contributor.editorLi, Tzu-Maoen_US
dc.date.accessioned2025-05-09T09:35:09Z
dc.date.available2025-05-09T09:35:09Z
dc.date.issued2025
dc.description.abstractDespite 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.en_US
dc.description.sectionheadersShort Paper 1
dc.description.seriesinformationEurographics 2025 - Short Papers
dc.identifier.doi10.2312/egs.20251030
dc.identifier.isbn978-3-03868-268-4
dc.identifier.issn1017-4656
dc.identifier.pages4 pages
dc.identifier.urihttps://doi.org/10.2312/egs.20251030
dc.identifier.urihttps://diglib.eg.org/handle/10.2312/egs20251030
dc.publisherThe Eurographics Associationen_US
dc.rightsAttribution 4.0 International License
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/
dc.subjectCCS Concepts: Computing methodologies → Artificial intelligence; Neural networks; Image-based rendering
dc.subjectComputing methodologies → Artificial intelligence
dc.subjectNeural networks
dc.subjectImage
dc.subjectbased rendering
dc.titleCardioid Caustics Generation with Conditional Diffusion Modelsen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
egs20251030.pdf
Size:
4.84 MB
Format:
Adobe Portable Document Format
Download
Collections
EG 2025 - Short Papers