A SVBRDF Modeling Pipeline using Pixel Clustering

TL;DR

This paper introduces a mobile phone-based pipeline for modeling spatially varying BRDFs of planar materials using minimal images, employing pixel clustering and optimization for high-quality results.

Contribution

It presents a lightweight, easy-to-use method for svBRDF modeling that requires only two photos and achieves high-quality texture synthesis.

Findings

Requires only two photos for data acquisition

Produces high-quality svBRDF parameters, normal, and tangent maps

Lightweight and easy-to-use pipeline

Abstract

We present a pipeline for modeling spatially varying BRDFs (svBRDFs) of planar materials which only requires a mobile phone for data acquisition. With a minimum of two photos under the ambient and point light source, our pipeline produces svBRDF parameters, a normal map and a tangent map for the material sample. The BRDF fitting is achieved via a pixel clustering strategy and an optimization based scheme. Our method is light-weight, easy-to-use and capable of producing high-quality BRDF textures.