Multi-view Inverse Rendering for Large-scale Real-world Indoor Scenes

TL;DR

This paper introduces a novel multi-view inverse rendering approach for large indoor scenes, utilizing a compact Texture-based Lighting representation to efficiently model global illumination and physically plausible materials, enabling advanced editing and relighting applications.

Contribution

It proposes a new compact lighting representation called Texture-based Lighting (TBL) and a three-stage material optimization strategy for large-scale indoor scene reconstruction.

Findings

Outperforms state-of-the-art methods quantitatively and qualitatively.

Enables realistic material editing, view synthesis, and relighting.

Improves efficiency and reduces noise in large-scale scene rendering.

Abstract

We present a efficient multi-view inverse rendering method for large-scale real-world indoor scenes that reconstructs global illumination and physically-reasonable SVBRDFs. Unlike previous representations, where the global illumination of large scenes is simplified as multiple environment maps, we propose a compact representation called Texture-based Lighting (TBL). It consists of 3D mesh and HDR textures, and efficiently models direct and infinite-bounce indirect lighting of the entire large scene. Based on TBL, we further propose a hybrid lighting representation with precomputed irradiance, which significantly improves the efficiency and alleviates the rendering noise in the material optimization. To physically disentangle the ambiguity between materials, we propose a three-stage material optimization strategy based on the priors of semantic segmentation and room segmentation. Extensive experiments show that the proposed method outperforms the state-of-the-art quantitatively and qualitatively, and enables physically-reasonable mixed-reality applications such as material editing, editable novel view synthesis and relighting. The project page is at https://lzleejean.github.io/TexIR.