SIRe-IR: Inverse Rendering for BRDF Reconstruction with Shadow and Illumination Removal in High-Illuminance Scenes
This addresses the challenge of accurate BRDF reconstruction in high-illuminance scenes for computer vision and graphics applications, representing an incremental improvement over prior implicit neural methods.
The paper tackles the problem of inverse rendering in strongly illuminated scenes with shadows and indirect illumination, which existing methods struggle with, and presents SIRe-IR, an implicit neural approach that removes shadows and indirect illumination to recover high-quality albedo and roughness, outperforming existing methods in evaluations.
Implicit neural representation has opened up new possibilities for inverse rendering. However, existing implicit neural inverse rendering methods struggle to handle strongly illuminated scenes with significant shadows and indirect illumination. The existence of shadows and reflections can lead to an inaccurate understanding of scene geometry, making precise factorization difficult. To this end, we present SIRe-IR, an implicit neural inverse rendering approach that uses non-linear mapping and regularized visibility estimation to decompose the scene into environment map, albedo, and roughness. By accurately modeling the indirect radiance field, normal, visibility, and direct light simultaneously, we are able to remove both shadows and indirect illumination in materials without imposing strict constraints on the scene. Even in the presence of intense illumination, our method recovers high-quality albedo and roughness with no shadow interference. SIRe-IR outperforms existing methods in both quantitative and qualitative evaluations.