RISE-SDF: a Relightable Information-Shared Signed Distance Field for Glossy Object Inverse Rendering

TL;DR

This paper introduces RISE-SDF, a neural inverse rendering system that accurately reconstructs geometry and materials of glossy objects, enabling realistic relighting through a novel two-stage, physically-based approach with a new evaluation dataset.

Contribution

The paper presents a two-stage neural inverse rendering method with a shared information network and a new dataset for glossy object relighting, advancing the state-of-the-art in inverse rendering accuracy.

Findings

Achieves state-of-the-art inverse rendering performance.

Excels in reconstructing highly reflective objects.

Provides a new dataset for quantitative evaluation.

Abstract

In this paper, we propose a novel end-to-end relightable neural inverse rendering system that achieves high-quality reconstruction of geometry and material properties, thus enabling high-quality relighting. The cornerstone of our method is a two-stage approach for learning a better factorization of scene parameters. In the first stage, we develop a reflection-aware radiance field using a neural signed distance field (SDF) as the geometry representation and deploy an MLP (multilayer perceptron) to estimate indirect illumination. In the second stage, we introduce a novel information-sharing network structure to jointly learn the radiance field and the physically based factorization of the scene. For the physically based factorization, to reduce the noise caused by Monte Carlo sampling, we apply a split-sum approximation with a simplified Disney BRDF and cube mipmap as the environment light representation. In the relighting phase, to enhance the quality of indirect illumination, we propose a second split-sum algorithm to trace secondary rays under the split-sum rendering framework. Furthermore, there is no dataset or protocol available to quantitatively evaluate the inverse rendering performance for glossy objects. To assess the quality of material reconstruction and relighting, we have created a new dataset with ground truth BRDF parameters and relighting results. Our experiments demonstrate that our algorithm achieves state-of-the-art performance in inverse rendering and relighting, with particularly strong results in the reconstruction of highly reflective objects.