TEXTure: Text-Guided Texturing of 3D Shapes

TL;DR

TEXTure introduces a novel text-guided method for generating, editing, and transferring textures on 3D shapes using a depth-to-image diffusion model, addressing consistency issues with an innovative trimap-based sampling process.

Contribution

The paper presents a new diffusion-based approach for seamless 3D texture generation, transfer, and editing without explicit surface mapping or reconstruction.

Findings

Effective texture generation from single viewpoints

Seamless texture transfer to new geometries

Ability to edit textures with text or scribbles

Abstract

In this paper, we present TEXTure, a novel method for text-guided generation, editing, and transfer of textures for 3D shapes. Leveraging a pretrained depth-to-image diffusion model, TEXTure applies an iterative scheme that paints a 3D model from different viewpoints. Yet, while depth-to-image models can create plausible textures from a single viewpoint, the stochastic nature of the generation process can cause many inconsistencies when texturing an entire 3D object. To tackle these problems, we dynamically define a trimap partitioning of the rendered image into three progression states, and present a novel elaborated diffusion sampling process that uses this trimap representation to generate seamless textures from different views. We then show that one can transfer the generated texture maps to new 3D geometries without requiring explicit surface-to-surface mapping, as well as extract semantic textures from a set of images without requiring any explicit reconstruction. Finally, we show that TEXTure can be used to not only generate new textures but also edit and refine existing textures using either a text prompt or user-provided scribbles. We demonstrate that our TEXTuring method excels at generating, transferring, and editing textures through extensive evaluation, and further close the gap between 2D image generation and 3D texturing.