Modeling Indirect Illumination for Inverse Rendering
This work addresses the challenge of inverse rendering for computer vision and graphics researchers, offering an incremental improvement by specifically handling indirect illumination more efficiently than prior approaches.
The paper tackles the problem of recovering geometry and materials from multi-view RGB images under unknown static illumination by efficiently modeling indirect illumination, which previous methods often neglect due to computational cost. The result is a method that recovers interreflection- and shadow-free albedo, demonstrating superior performance on synthetic and real data with realistic renderings under novel viewpoints and illumination.
Recent advances in implicit neural representations and differentiable rendering make it possible to simultaneously recover the geometry and materials of an object from multi-view RGB images captured under unknown static illumination. Despite the promising results achieved, indirect illumination is rarely modeled in previous methods, as it requires expensive recursive path tracing which makes the inverse rendering computationally intractable. In this paper, we propose a novel approach to efficiently recovering spatially-varying indirect illumination. The key insight is that indirect illumination can be conveniently derived from the neural radiance field learned from input images instead of being estimated jointly with direct illumination and materials. By properly modeling the indirect illumination and visibility of direct illumination, interreflection- and shadow-free albedo can be recovered. The experiments on both synthetic and real data demonstrate the superior performance of our approach compared to previous work and its capability to synthesize realistic renderings under novel viewpoints and illumination. Our code and data are available at https://zju3dv.github.io/invrender/.