NePF: Neural Photon Field for Single-Stage Inverse Rendering
This addresses the complexity of multi-stage inverse rendering methods for computer vision and graphics applications, though it appears incremental in unifying existing components.
The paper tackles the ill-posed problem of inverse rendering from multi-view images by proposing NePF, a single-stage framework that uniformly recovers geometry, material, and illumination properties, achieving high-fidelity geometry and visually plausible material attributes on real and synthetic datasets.
We present a novel single-stage framework, Neural Photon Field (NePF), to address the ill-posed inverse rendering from multi-view images. Contrary to previous methods that recover the geometry, material, and illumination in multiple stages and extract the properties from various multi-layer perceptrons across different neural fields, we question such complexities and introduce our method - a single-stage framework that uniformly recovers all properties. NePF achieves this unification by fully utilizing the physical implication behind the weight function of neural implicit surfaces and the view-dependent radiance. Moreover, we introduce an innovative coordinate-based illumination model for rapid volume physically-based rendering. To regularize this illumination, we implement the subsurface scattering model for diffuse estimation. We evaluate our method on both real and synthetic datasets. The results demonstrate the superiority of our approach in recovering high-fidelity geometry and visual-plausible material attributes.