Triplet: Triangle Patchlet for Mesh-Based Inverse Rendering and Scene Parameters Approximation

TL;DR

This paper presents Triplet, a mesh-based framework that accurately estimates scene light, geometry, and materials for inverse rendering, outperforming existing methods in visual quality and parameter accuracy.

Contribution

Introduction of Triplet, a novel mesh-based representation for comprehensive inverse scene parameter estimation using physical simulation and iterative optimization.

Findings

Achieves state-of-the-art visual quality in inverse rendering.

Reconstructs high-quality geometry and accurate material properties.

Effectively estimates scene light, geometry, and materials without prior knowledge.

Abstract

Recent advancements in Radiance Fields have significantly improved novel-view synthesis. However, in many real-world applications, the more advanced challenge lies in inverse rendering, which seeks to derive the physical properties of a scene, including light, geometry, textures, and materials. Meshes, as a traditional representation adopted by many simulation pipeline, however, still show limited influence in radiance field for inverse rendering. This paper introduces a novel framework called Triangle Patchlet (abbr. Triplet), a mesh-based representation, to comprehensively approximate these scene parameters. We begin by assembling Triplets with either randomly generated points or sparse points obtained from camera calibration where all faces are treated as an independent element. Next, we simulate the physical interaction of light and optimize the scene parameters using traditional graphics rendering techniques like rasterization and ray tracing, accompanying with density control and propagation. An iterative mesh extracting process is also suggested, where we continue to optimize on geometry and materials with graph-based operation. We also introduce several regulation terms to enable better generalization of materials property. Our framework could precisely estimate the light, materials and geometry with mesh without prior of light, materials and geometry in a unified framework. Experiments demonstrate that our approach can achieve state-of-the-art visual quality while reconstructing high-quality geometry and accurate material properties.