Environmental volumetric neural shading of clouds for real-time rendering
Olajos, Rikard LU
; Doggett, Michael
LU
and Goswami, Prashant
(2026)
In Proceedings of the ACM on Computer Graphics and Interactive Techniques
9(4).
- Abstract
- We present a high-performance method for real-time relighting of high-fidelity volumetric clouds. Building on Relightable Neural Assets, we introduce key adaptations that enable neural shading of volumetric cloud phenomena within a rasterization-based pipeline. In particular, we incorporate a per-pixel thickness parameter to capture view-dependent opacity and replace the generalizing single light source with a sky illumination model, allowing the network to learn complex atmospheric scattering effects. To achieve real-time performance, we depart from density-field-based volumetric rendering and instead operate on mesh representations combined with a triplane feature encoding. This enables a fully rasterization-driven solution that... (More)
- We present a high-performance method for real-time relighting of high-fidelity volumetric clouds. Building on Relightable Neural Assets, we introduce key adaptations that enable neural shading of volumetric cloud phenomena within a rasterization-based pipeline. In particular, we incorporate a per-pixel thickness parameter to capture view-dependent opacity and replace the generalizing single light source with a sky illumination model, allowing the network to learn complex atmospheric scattering effects. To achieve real-time performance, we depart from density-field-based volumetric rendering and instead operate on mesh representations combined with a triplane feature encoding. This enables a fully rasterization-driven solution that reproduces volumetric appearance without requiring ray marching or volume integration. We further describe a complete pipeline for converting volumetric cloud assets into a neural representation trained from path-traced supervision. We evaluate our method through an ablation study analyzing both image quality and runtime performance. Our adaptations improve reconstruction quality from 18.13 dB to 22.32 dB while achieving rendering times as low as 3.7 ms per frame. These results demonstrate that our approach enables high-quality, relightable cloud rendering suitable for real-time and performance-critical applications. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/b4907c00-161e-4b9a-9f54-318aebae74c7
- author
- Olajos, Rikard
LU
; Doggett, Michael
LU
and Goswami, Prashant
- organization
- publishing date
- 2026-06-29
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Proceedings of the ACM on Computer Graphics and Interactive Techniques
- volume
- 9
- issue
- 4
- pages
- 17 pages
- publisher
- Association for Computing Machinery (ACM)
- ISSN
- 2577-6193
- DOI
- 10.1145/3820020
- project
- Real-Time Realistic Pixel Synthesis using Deep Learning for Augmented and Virtual Reality
- language
- English
- LU publication?
- yes
- id
- b4907c00-161e-4b9a-9f54-318aebae74c7
- date added to LUP
- 2026-07-02 11:08:57
- date last changed
- 2026-09-16 15:03:25
@article{b4907c00-161e-4b9a-9f54-318aebae74c7,
abstract = {{We present a high-performance method for real-time relighting of high-fidelity volumetric clouds. Building on Relightable Neural Assets, we introduce key adaptations that enable neural shading of volumetric cloud phenomena within a rasterization-based pipeline. In particular, we incorporate a per-pixel thickness parameter to capture view-dependent opacity and replace the generalizing single light source with a sky illumination model, allowing the network to learn complex atmospheric scattering effects. To achieve real-time performance, we depart from density-field-based volumetric rendering and instead operate on mesh representations combined with a triplane feature encoding. This enables a fully rasterization-driven solution that reproduces volumetric appearance without requiring ray marching or volume integration. We further describe a complete pipeline for converting volumetric cloud assets into a neural representation trained from path-traced supervision. We evaluate our method through an ablation study analyzing both image quality and runtime performance. Our adaptations improve reconstruction quality from 18.13 dB to 22.32 dB while achieving rendering times as low as 3.7 ms per frame. These results demonstrate that our approach enables high-quality, relightable cloud rendering suitable for real-time and performance-critical applications.}},
author = {{Olajos, Rikard and Doggett, Michael and Goswami, Prashant}},
issn = {{2577-6193}},
language = {{eng}},
month = {{06}},
number = {{4}},
publisher = {{Association for Computing Machinery (ACM)}},
series = {{Proceedings of the ACM on Computer Graphics and Interactive Techniques}},
title = {{Environmental volumetric neural shading of clouds for real-time rendering}},
url = {{http://dx.doi.org/10.1145/3820020}},
doi = {{10.1145/3820020}},
volume = {{9}},
year = {{2026}},
}