IBL‐NeRF: Image‐Based Lighting Formulation of Neural Radiance Fields
- 30 October 2023
- journal article
- research article
- Published by Wiley in Computer Graphics Forum
- Vol. 42 (7)
Abstract
We propose IBL‐NeRF, which decomposes the neural radiance fields (NeRF) of large‐scale indoor scenes into intrinsic components. Recent approaches further decompose the baked radiance of the implicit volume into intrinsic components such that one can partially approximate the rendering equation. However, they are limited to representing isolated objects with a shared environment lighting, and suffer from computational burden to aggregate rays with Monte Carlo integration. In contrast, our prefiltered radiance field extends the original NeRF formulation to capture the spatial variation of lighting within the scene volume, in addition to surface properties. Specifically, the scenes of diverse materials are decomposed into intrinsic components for rendering, namely, albedo, roughness, surface normal, irradiance, and prefiltered radiance. All of the components are inferred as neural images from MLP, which can model large‐scale general scenes. Especially the prefiltered radiance effectively models the volumetric light field, and captures spatial variation beyond a single environment light. The prefiltering aggregates rays in a set of predefined neighborhood sizes such that we can replace the costly Monte Carlo integration of global illumination with a simple query from a neural image. By adopting NeRF, our approach inherits superior visual quality and multi‐view consistency for synthesized images as well as the intrinsic components. We demonstrate the performance on scenes with complex object layouts and light configurations, which could not be processed in any of the previous works.Keywords
All Related Versions
Funding Information
- Korea Institute for Advancement of Technology
- Ministry of Trade, Industry and Energy (P0012746)
This publication has 28 references indexed in Scilit:
- CGIntrinsics: Better Intrinsic Image Decomposition Through Physically-Based Rendering2018
- ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes2017
- Structure-from-Motion Revisited2016
- Learning Data-Driven Reflectance Priors for Intrinsic Image Decomposition2015
- Multiview Intrinsic Images of Outdoors Scenes with an Application to RelightingACM Transactions on Graphics, 2015
- Intrinsic images in the wildACM Transactions on Graphics, 2014
- Coherent intrinsic images from photo collectionsACM Transactions on Graphics, 2012
- Intrinsic Images by ClusteringComputer Graphics Forum, 2012
- OptiXACM Transactions on Graphics, 2010
- The rendering equation1986