Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gai, Meng, Wang, Guoping, Li, Sheng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909887760433152
author Gai, Meng
Wang, Guoping
Li, Sheng
author_facet Gai, Meng
Wang, Guoping
Li, Sheng
contents Real-time rendering with global illumination is crucial to afford the user realistic experience in virtual environments. We present a learning-based estimator to predict diffuse indirect illumination in screen space, which then is combined with direct illumination to synthesize globally-illuminated high dynamic range (HDR) results. Our approach tackles the challenges of capturing long-range/long-distance indirect illumination when employing neural networks and is generalized to handle complex lighting and scenarios. From the neural network thinking of the solver to the rendering equation, we present a novel network architecture to predict indirect illumination. Our network is equipped with a modified attention mechanism that aggregates global information guided by spacial geometry features, as well as a monochromatic design that encodes each color channel individually. We conducted extensive evaluations, and the experimental results demonstrate our superiority over previous learning-based techniques. Our approach excels at handling complex lighting such as varying-colored lighting and environment lighting. It can successfully capture distant indirect illumination and simulates the interreflections between textured surfaces well (i.e., color bleeding effects); it can also effectively handle new scenes that are not present in the training dataset.
format Preprint
id arxiv_https___arxiv_org_abs_2508_08826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination
Gai, Meng
Wang, Guoping
Li, Sheng
Graphics
Artificial Intelligence
Real-time rendering with global illumination is crucial to afford the user realistic experience in virtual environments. We present a learning-based estimator to predict diffuse indirect illumination in screen space, which then is combined with direct illumination to synthesize globally-illuminated high dynamic range (HDR) results. Our approach tackles the challenges of capturing long-range/long-distance indirect illumination when employing neural networks and is generalized to handle complex lighting and scenarios. From the neural network thinking of the solver to the rendering equation, we present a novel network architecture to predict indirect illumination. Our network is equipped with a modified attention mechanism that aggregates global information guided by spacial geometry features, as well as a monochromatic design that encodes each color channel individually. We conducted extensive evaluations, and the experimental results demonstrate our superiority over previous learning-based techniques. Our approach excels at handling complex lighting such as varying-colored lighting and environment lighting. It can successfully capture distant indirect illumination and simulates the interreflections between textured surfaces well (i.e., color bleeding effects); it can also effectively handle new scenes that are not present in the training dataset.
title Geometry-Aware Global Feature Aggregation for Real-Time Indirect Illumination
topic Graphics
Artificial Intelligence
url https://arxiv.org/abs/2508.08826