Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models

TL;DR

Paint3D introduces a new generative framework that creates high-resolution, lighting-less 2K UV textures for 3D meshes from text or images, enabling re-lighting and editing within graphics pipelines.

Contribution

The paper proposes a novel coarse-to-fine diffusion-based method for generating high-quality, lighting-less 3D textures conditioned on text or images, addressing limitations of existing 2D models.

Findings

Produces 2K high-resolution textures with semantic consistency

Effectively removes lighting artifacts and incomplete areas

Enables re-lighting and editing of textures in graphics pipelines

Abstract

This paper presents Paint3D, a novel coarse-to-fine generative framework that is capable of producing high-resolution, lighting-less, and diverse 2K UV texture maps for untextured 3D meshes conditioned on text or image inputs. The key challenge addressed is generating high-quality textures without embedded illumination information, which allows the textures to be re-lighted or re-edited within modern graphics pipelines. To achieve this, our method first leverages a pre-trained depth-aware 2D diffusion model to generate view-conditional images and perform multi-view texture fusion, producing an initial coarse texture map. However, as 2D models cannot fully represent 3D shapes and disable lighting effects, the coarse texture map exhibits incomplete areas and illumination artifacts. To resolve this, we train separate UV Inpainting and UVHD diffusion models specialized for the shape-aware refinement of incomplete areas and the removal of illumination artifacts. Through this coarse-to-fine process, Paint3D can produce high-quality 2K UV textures that maintain semantic consistency while being lighting-less, significantly advancing the state-of-the-art in texturing 3D objects.