MaPa: Text-driven Photorealistic Material Painting for 3D Shapes
This addresses the problem of creating editable, high-quality 3D materials from text for applications in computer graphics and design, representing a novel approach but with incremental elements in method integration.
The paper tackles generating materials for 3D meshes from text descriptions by proposing a method that uses segment-wise procedural material graphs and leverages a pre-trained 2D diffusion model, resulting in superior performance in photorealism, resolution, and editability over existing methods.
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