NDJIR: Neural Direct and Joint Inverse Rendering for Geometry, Lights, and Materials of Real Object
This work addresses the challenge of accurately decomposing scene properties for computer graphics and vision applications, representing an incremental improvement by directly using physically-based rendering without approximations.
The paper tackles the problem of inverse rendering to decompose geometry, lights, and materials from multi-view images, proposing NDJIR, which directly addresses integrals in the rendering equation and jointly decomposes these components, showing semantically well decomposition for real objects in photogrammetric settings.
The goal of inverse rendering is to decompose geometry, lights, and materials given pose multi-view images. To achieve this goal, we propose neural direct and joint inverse rendering, NDJIR. Different from prior works which relies on some approximations of the rendering equation, NDJIR directly addresses the integrals in the rendering equation and jointly decomposes geometry: signed distance function, lights: environment and implicit lights, materials: base color, roughness, specular reflectance using the powerful and flexible volume rendering framework, voxel grid feature, and Bayesian prior. Our method directly uses the physically-based rendering, so we can seamlessly export an extracted mesh with materials to DCC tools and show material conversion examples. We perform intensive experiments to show that our proposed method can decompose semantically well for real object in photogrammetric setting and what factors contribute towards accurate inverse rendering.