Text-Guided Texturing by Synchronized Multi-View Diffusion
This solves the texture inconsistency issue in 3D texturing for applications like computer graphics and virtual reality, representing an incremental improvement over existing project-and-inpaint methods.
The paper tackles the problem of inconsistent texture generation for 3D objects from text prompts by addressing asynchronous diffusion in multi-view methods, proposing a synchronized approach that shares denoised content across views to achieve consistent, seamless, and highly detailed textures with superior performance compared to state-of-the-art methods.
This paper introduces a novel approach to synthesize texture to dress up a given 3D object, given a text prompt. Based on the pretrained text-to-image (T2I) diffusion model, existing methods usually employ a project-and-inpaint approach, in which a view of the given object is first generated and warped to another view for inpainting. But it tends to generate inconsistent texture due to the asynchronous diffusion of multiple views. We believe such asynchronous diffusion and insufficient information sharing among views are the root causes of the inconsistent artifact. In this paper, we propose a synchronized multi-view diffusion approach that allows the diffusion processes from different views to reach a consensus of the generated content early in the process, and hence ensures the texture consistency. To synchronize the diffusion, we share the denoised content among different views in each denoising step, specifically blending the latent content in the texture domain from views with overlap. Our method demonstrates superior performance in generating consistent, seamless, highly detailed textures, comparing to state-of-the-art methods.