MD-ProjTex: Texturing 3D Shapes with Multi-Diffusion Projection
This addresses text-guided 3D texturing for applications like graphics and design, representing an incremental improvement over prior methods.
The paper tackles the problem of generating consistent textures for 3D shapes from text prompts, achieving better quantitative and qualitative results with computational efficiency compared to existing state-of-the-art methods.
We introduce MD-ProjTex, a method for fast and consistent text-guided texture generation for 3D shapes using pretrained text-to-image diffusion models. At the core of our approach is a multi-view consistency mechanism in UV space, which ensures coherent textures across different viewpoints. Specifically, MD-ProjTex fuses noise predictions from multiple views at each diffusion step and jointly updates the per-view denoising directions to maintain 3D consistency. In contrast to existing state-of-the-art methods that rely on optimization or sequential view synthesis, MD-ProjTex is computationally more efficient and achieves better quantitative and qualitative results.