MaPa: Text-driven Photorealistic Material Painting for 3D Shapes

TL;DR

MaPa introduces a novel text-driven method for generating high-quality, editable, segment-wise procedural materials for 3D shapes by leveraging pre-trained 2D diffusion models and differentiable rendering.

Contribution

It proposes a new approach that uses diffusion models to connect text descriptions with procedural material graphs for 3D shapes, avoiding extensive paired data.

Findings

Outperforms existing methods in photorealism and resolution

Supports flexible editing of generated materials

Demonstrates high-quality, text-aligned material synthesis

Abstract

This paper aims to generate materials for 3D meshes from text descriptions. Unlike existing methods that synthesize texture maps, we propose to generate segment-wise procedural material graphs as the appearance representation, which supports high-quality rendering and provides substantial flexibility in editing. Instead of relying on extensive paired data, i.e., 3D meshes with material graphs and corresponding text descriptions, to train a material graph generative model, we propose to leverage the pre-trained 2D diffusion model as a bridge to connect the text and material graphs. Specifically, our approach decomposes a shape into a set of segments and designs a segment-controlled diffusion model to synthesize 2D images that are aligned with mesh parts. Based on generated images, we initialize parameters of material graphs and fine-tune them through the differentiable rendering module to produce materials in accordance with the textual description. Extensive experiments demonstrate the superior performance of our framework in photorealism, resolution, and editability over existing methods. Project page: https://zju3dv.github.io/MaPa