3秒生成高精度3D纹理，支持文本驱动与多视角一致
Make-A-Texture: Fast Shape-Aware Texture Generation in 3 Seconds
- 用深度感知扩散模型逐视角生成纹理，自动选最优视点序列
- 单张H100 GPU仅需3.07秒完成全图生成，速度领先现有方法
- 减少背面与非正面面片伪影，适合实时交互与文本编辑场景
我们提出Make-A-Texture，一种高效生成高分辨率纹理贴图的新框架，可根据文本提示为给定3D几何体生成纹理。该方法通过深度感知的修补扩散模型，按自动视点选择算法确定的优化序列，逐步生成多视角一致的纹理。其显著优势在于极高的效率：在单张NVIDIA H100 GPU上，端到端运行时间仅3.07秒，显著优于现有方法。这一加速得益于扩散模型优化和专用的反投影方法。此外，通过有选择地屏蔽非前向面及开表面物体的内部面，有效降低了反投影阶段的伪影。实验表明，Make-A-Texture在质量上达到或超越当前最先进方法。本工作大幅提升了纹理生成模型在真实3D内容创作中的实用性，尤其适用于交互式创作与文本引导的纹理编辑。
原文摘要 · Abstract (English)
We present Make-A-Texture, a new framework that efficiently synthesizes high-resolution texture maps from textual prompts for given 3D geometries. Our approach progressively generates textures that are consistent across multiple viewpoints with a depth-aware inpainting diffusion model, in an optimized sequence of viewpoints determined by an automatic view selection algorithm. A significant feature of our method is its remarkable efficiency, achieving a full texture generation within an end-to-end runtime of just 3.07 seconds on a single NVIDIA H100 GPU, significantly outperforming existing methods. Such an acceleration is achieved by optimizations in the diffusion model and a specialized backprojection method. Moreover, our method reduces the artifacts in the backprojection phase, by selectively masking out non-frontal faces, and internal faces of open-surfaced objects. Experimental results demonstrate that Make-A-Texture matches or exceeds the quality of other state-of-the-art methods. Our work significantly improves the applicability and practicality of texture generation models for real-world 3D content creation, including interactive creation and text-guided texture editing.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。