用文本生成3D材质贴图，速度快且全局一致
PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models
- 通过视图打包提升多视角生成分辨率，不增加推理开销
- 在相同时间内生成更高分辨率贴图，质量超越现有方法
- 适合需要高效高质量3D材质生成的设计师与开发者
我们提出PacTure，一种从文本描述生成无纹理3D网格物理渲染（PBR）材质贴图的新框架。现有基于2D生成的贴图方法要么按不同视角顺序生成，导致推理时间长且全局不一致；要么采用多视角生成并引入跨视角注意力以提升一致性，但限制了单视角分辨率。针对这些问题，我们首次提出视图打包技术，在多视角生成中显著提高每视角的有效分辨率，且不增加额外推理成本。该方法不依赖UV映射，保留图像生成所需的空间邻近性，并与现有2D生成模型完全兼容。为进一步降低推理成本，我们在自回归框架中实现细粒度控制与多领域生成，构建高效多视角PBR生成骨干。大量实验表明，PacTure在质量和效率上均优于当前最优方法。
原文摘要 · Abstract (English)
We present PacTure, a novel framework for generating physically-based rendering (PBR) material textures for an untextured 3D mesh from a text description. Existing 2D generation-based texturing approaches either generate textures sequentially from different views, resulting in long inference times and globally inconsistent textures, or adopt multi-view generation with cross-view attention to enhance global consistency, which, however, limits the resolution for each view. In response to these weaknesses, we first introduce view packing, a novel technique that significantly increases the effective resolution for each view during multi-view generation, without imposing additional inference cost. Unlike UV mapping, it preserves the spatial proximity essential for image generation and maintains full compatibility with current 2D generative models. To further reduce the inferencing cost, we enable fine-grained control and multi-domain generation within the next-scale prediction autoregressive framework, creating an efficient multi-view PBR generation backbone. Extensive experiments show that PacTure outperforms state-of-the-art methods in both quality and efficiency.
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。