Floating Radiance Networks

2026-08-06

AI Summary

This work proposes a hybrid neural scene representation that unifies explicit, ray-traceable geometry with continuous neural radiance fields, addressing the limitations of existing methods that are often confined to a single rendering paradigm and incompatible with conventional graphics pipelines. The approach introduces floating-plane generalized Gaussian primitives, each augmented with a local latent descriptor encoding a neural radiance field. By integrating a shared lightweight decoder, hardware-accelerated primitive-ray intersection, and latent-space mapping, the method achieves competitive rendering quality using a compact set of primitives on standard reconstruction benchmarks. It natively supports interactive ray tracing, geometric editing, appearance stylization, and advanced rendering effects such as reflections, refractions, transparency, and shadows.

Abstract

Recent advances in neural scene representations enable photorealistic novel-view synthesis, yet most methods remain tightly coupled to a single rendering paradigm, limiting their versatility and integration with conventional graphics workflows. We introduce Floating Radiance Networks (FlaRe), a neural scene representation combining explicit ray-traceable geometry with continuous neural radiance functions. A scene is represented by floating planar generalized Gaussian primitives, each carrying a compact latent descriptor of a local radiance field. A lightweight decoder shared across the scene maps this descriptor, local surface coordinates, and viewing direction to color and opacity. This formulation preserves the expressiveness of neural fields while providing an explicitly addressable structure that can be efficiently queried and manipulated. Hardware-accelerated primitive intersections enable interactive rendering and recursive ray-tracing, including reflections, refractions, transparency, and shadows. The same representation further supports primitive-level deformation, mesh extraction, and appearance stylization directly in its learned descriptor space. Experiments across standard reconstruction benchmarks demonstrate competitive rendering quality while using a compact set of primitives. Together, these results establish FlaRe as a versatile representation that brings high-fidelity neural rendering, ray-tracing, geometric manipulation, and appearance editing into a unified scene model. Source code is available online. Source code can be found at: https://github.com/KByrski/FlaRe

Problem

• neural scene representation
• rendering paradigm
• graphics workflow
• versatility
• integration

Innovation

• neural scene representation
• ray tracing
• explicit geometry
• radiance fields
• interactive rendering