CVGRNov 28, 2023

Material Palette: Extraction of Materials from a Single Image

arXiv:2311.17060v136 citationsh-index: 21Has Code
Originality Incremental advance
AI Analysis

This addresses the challenge of material extraction for rendering applications, enabling editing of 3D scenes from photographs, but it is incremental as it builds on existing synthetic libraries and uses domain adaptation.

The paper tackles the problem of extracting physically-based rendering materials from a single real-world image, achieving this by mapping image regions to material concepts using a diffusion model and decomposing textures into SVBRDFs, with evaluation on synthetic and real-world datasets.

In this paper, we propose a method to extract physically-based rendering (PBR) materials from a single real-world image. We do so in two steps: first, we map regions of the image to material concepts using a diffusion model, which allows the sampling of texture images resembling each material in the scene. Second, we benefit from a separate network to decompose the generated textures into Spatially Varying BRDFs (SVBRDFs), providing us with materials ready to be used in rendering applications. Our approach builds on existing synthetic material libraries with SVBRDF ground truth, but also exploits a diffusion-generated RGB texture dataset to allow generalization to new samples using unsupervised domain adaptation (UDA). Our contributions are thoroughly evaluated on synthetic and real-world datasets. We further demonstrate the applicability of our method for editing 3D scenes with materials estimated from real photographs. The code and models will be made open-source. Project page: https://astra-vision.github.io/MaterialPalette/

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes