Neural Cone Radiosity for Interactive Global Illumination with Glossy Materials

2025-09-09

AI Summary

Existing neural radiance field methods struggle to model high-frequency, strongly view-dependent outgoing radiance distributions under glossy materials, leading to highlight distortion and noise in real-time global illumination. To address this, we propose Neural Cone Radiance—a novel representation that explicitly captures directional reflectance properties. Our approach introduces three key innovations: (1) a reflection-aware ray-cone encoding scheme that models anisotropic reflectance; (2) a pre-filtered multi-resolution hash grid that jointly encodes view-dependent reflectance and enables unified representation across the full gloss spectrum—from specular highlights to diffuse matte regions; and (3) continuous-space aggregation for efficient rendering. Evaluated on diverse glossy scenes, our method achieves real-time, noise-free, high-fidelity rendering. It significantly outperforms state-of-the-art baselines both qualitatively—delivering superior visual realism—and quantitatively—achieving higher PSNR, SSIM, and LPIPS scores.

Technology Category

• Computer Vision: 3D Computer Vision
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Modeling of high-frequency outgoing radiance distributions has long been a key challenge in rendering, particularly for glossy material. Such distributions concentrate radiative energy within a narrow lobe and are highly sensitive to changes in view direction. However, existing neural radiosity methods, which primarily rely on positional feature encoding, exhibit notable limitations in capturing these high-frequency, strongly view-dependent radiance distributions. To address this, we propose a highly-efficient approach by reflectance-aware ray cone encoding based on the neural radiosity framework, named neural cone radiosity. The core idea is to employ a pre-filtered multi-resolution hash grid to accurately approximate the glossy BSDF lobe, embedding view-dependent reflectance characteristics directly into the encoding process through continuous spatial aggregation. Our design not only significantly improves the network's ability to model high-frequency reflection distributions but also effectively handles surfaces with a wide range of glossiness levels, from highly glossy to low-gloss finishes. Meanwhile, our method reduces the network's burden in fitting complex radiance distributions, allowing the overall architecture to remain compact and efficient. Comprehensive experimental results demonstrate that our method consistently produces high-quality, noise-free renderings in real time under various glossiness conditions, and delivers superior fidelity and realism compared to baseline approaches.

Problem

• Modeling high-frequency outgoing radiance distributions for glossy materials
• Capturing view-dependent radiance with neural radiosity methods
• Handling surfaces with wide glossiness levels efficiently

Innovation

• Reflectance-aware ray cone encoding for glossy materials
• Pre-filtered multi-resolution hash grid approximation
• Continuous spatial aggregation for view-dependent characteristics