OctaOctree Neural Radiosity for Real-time Glossy Material Rendering

2026-06-07

AI Summary

Existing methods struggle to efficiently model high-frequency outgoing radiance, particularly when handling global illumination involving glossy and specular materials. This work proposes OctaOctree—a novel radiance representation that integrates an adaptive octree spatial structure with octahedral directional maps, uniquely embedding reflection-aware spatial-angular priors directly into the representation. By employing high spatial resolution in diffuse regions and coarse spatial granularity paired with high angular resolution in specular or glossy regions, the method achieves a unified and efficient encoding across the full spectrum from diffuse to sharp reflections. High-quality, direction-aware global illumination can be generated at primary hit points with only a single network query, significantly outperforming current neural radiosity and irradiance caching approaches in both fidelity and real-time performance.

Abstract

Modeling high-frequency outgoing radiance distributions remains a fundamental challenge in global illumination, especially for glossy and specular materials. Existing neural-based radiance caching methods commonly rely on positional feature encodings or spatially organized caches, which makes it difficult to represent sharp directional radiance variations without increasing the model complexity or sampling cost. To address this challenge, we propose OctaOctree, an efficient spatial-angular radiance representation for global illumination. OctaOctree organizes outgoing radiance with an adaptive octree in 3D space, and associates each spatial node with an octahedral directional map. By coupling the spatial hierarchy with direction-dependent storage, our representation allocates fine spatial resolution to local illumination and visibility changes, while using coarser spatial levels with richer angular resolution to capture glossy and specular radiance distributions. This design embeds a reflectance-aware spatial-angular prior directly into the radiance representation, reducing the burden on neural networks or reconstruction modules to recover high-frequency view-dependent effects from positional features alone. As a result, OctaOctree provides a compact and expressive neural encoding for a wide range of indirect illumination effects, from diffuse interreflection to sharp glossy reflections. Experiments demonstrate that our method produces high-quality, direction-aware global illumination with single network query at primary intersections, achieving improved fidelity and real-time performance compared with baseline neural radiosity and radiance caching approaches.

Problem

• global illumination
• glossy materials
• specular materials
• radiance distribution
• high-frequency effects

Innovation

• OctaOctree
• neural radiosity
• global illumination
• glossy materials
• spatial-angular representation