Light the Sprite: Pixel Art Dynamic Light Map Generation

Thumbnail Image
Files
egs20251032.pdf (3.92 MB)
Date
2025
Authors
Nikolov, Ivan
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association
Abstract
Correct lighting and shading are vital for pixel art design. Automating texture generation, such as normal, depth, and occlusion maps, has been a long-standing focus. We extend this by proposing a deep learning model that generates point and directional light maps from RGB pixel art sprites and specified light vectors. Our approach modifies a UNet architecture with CIN layers to incorporate positional and directional information, using ZoeDepth for training depth data. Testing on a popular pixel art dataset shows that the generated light maps closely match those from depth or normal maps, as well as from manual programs. The model effectively relights complex sprites across styles and functions in real time, enhancing artist workflows. The code and dataset are here - https://github.com/IvanNik17/light-sprite.
Description

CCS Concepts: Computing methodologies → Non-photorealistic rendering; Image-based rendering; Theory of computation → Machine learning theory

        
@inproceedings{
10.2312:egs.20251032
,
booktitle = {
Eurographics 2025 - Short Papers
},
editor = {
Ceylan, Duygu
 and 
Li, Tzu-Mao
},
title = {{
Light the Sprite: Pixel Art Dynamic Light Map Generation
}},
author = {
Nikolov, Ivan
},
year = {
2025
},
publisher = {
The Eurographics Association
},
ISSN = {
1017-4656
},
ISBN = {
978-3-03868-268-4
},
DOI = {
10.2312/egs.20251032
}
}
Citation
URI
https://doi.org/10.2312/egs.20251032
 https://diglib.eg.org/handle/10.2312/egs20251032
Collections
EG 2025 - Short Papers