Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Inverse Rendering of Glossy Objects via the Neural Plenoptic Function and Radiance Fields

About

Inverse rendering aims at recovering both geometry and materials of objects. It provides a more compatible reconstruction for conventional rendering engines, compared with the neural radiance fields (NeRFs). On the other hand, existing NeRF-based inverse rendering methods cannot handle glossy objects with local light interactions well, as they typically oversimplify the illumination as a 2D environmental map, which assumes infinite lights only. Observing the superiority of NeRFs in recovering radiance fields, we propose a novel 5D Neural Plenoptic Function (NeP) based on NeRFs and ray tracing, such that more accurate lighting-object interactions can be formulated via the rendering equation. We also design a material-aware cone sampling strategy to efficiently integrate lights inside the BRDF lobes with the help of pre-filtered radiance fields. Our method has two stages: the geometry of the target object and the pre-filtered environmental radiance fields are reconstructed in the first stage, and materials of the target object are estimated in the second stage with the proposed NeP and material-aware cone sampling strategy. Extensive experiments on the proposed real-world and synthetic datasets demonstrate that our method can reconstruct high-fidelity geometry/materials of challenging glossy objects with complex lighting interactions from nearby objects. Project webpage: https://whyy.site/paper/nep

Haoyuan Wang, Wenbo Hu, Lei Zhu, Rynson W. H. Lau• 2024

Related benchmarks

TaskDatasetResultRank
Geometry ReconstructionSynthetic Objects (test)
Chamfer Distance (CD)0.0014
24
Material EstimationSynthetic Objects (test)
Roughness MSE0.001
12
Showing 2 of 2 rows

Other info

Code

Follow for update