Parametric Integration with Neural Integral Operators
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912498310971392 |
|---|---|
| author | Schied, Christoph Keller, Alexander |
| author_facet | Schied, Christoph Keller, Alexander |
| contents | Real-time rendering imposes strict limitations on the sampling budget for light transport simulation, often resulting in noisy images. However, denoisers have demonstrated that it is possible to produce noise-free images through filtering. We enhance image quality by removing noise before material shading, rather than filtering already shaded noisy images. This approach allows for material-agnostic denoising (MAD) and leverages machine learning by approximating the light transport integral operator with a neural network, effectively performing parametric integration with neural operators. Our method operates in real-time, requires data from only a single frame, seamlessly integrates with existing denoisers and temporal anti-aliasing techniques, and is efficient to train. Additionally, it is straightforward to incorporate with physically based rendering algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_17440 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Parametric Integration with Neural Integral Operators Schied, Christoph Keller, Alexander Graphics Real-time rendering imposes strict limitations on the sampling budget for light transport simulation, often resulting in noisy images. However, denoisers have demonstrated that it is possible to produce noise-free images through filtering. We enhance image quality by removing noise before material shading, rather than filtering already shaded noisy images. This approach allows for material-agnostic denoising (MAD) and leverages machine learning by approximating the light transport integral operator with a neural network, effectively performing parametric integration with neural operators. Our method operates in real-time, requires data from only a single frame, seamlessly integrates with existing denoisers and temporal anti-aliasing techniques, and is efficient to train. Additionally, it is straightforward to incorporate with physically based rendering algorithms. |
| title | Parametric Integration with Neural Integral Operators |
| topic | Graphics |
| url | https://arxiv.org/abs/2507.17440 |