This paper presents a novel method to generate textures for 3D models given text prompts and 3D meshes. Additional depth information is taken into account to perform the Score Distillation Sampling (SDS) process with depth conditional Stable Diffusion. We ran our model over the open-source dataset Objaverse and conducted a user study to compare the results with those of various 3D texturing methods. We have shown that our model can generate more satisfactory results and produce various art styles for the same object. In addition, we achieved faster time when generating textures of comparable quality. We also conduct thorough ablation studies of how different factors may affect generation quality, including sampling steps, guidance scale, negative prompts, data augmentation, elevation range, and alternatives to SDS.

翻译：本文提出了一种新颖方法，可根据文本提示与3D网格为三维模型生成纹理。通过引入深度信息，该方法利用深度条件化稳定扩散模型执行分数蒸馏采样（SDS）过程。我们在开源数据集Objaverse上运行模型，并开展用户研究，将其结果与多种3D纹理生成方法进行对比。实验表明，本模型可生成更令人满意的结果，并为同一对象呈现多样化艺术风格。此外，在生成质量相近的纹理时，我们实现了更快的处理速度。我们还进行了全面的消融研究，系统分析了采样步数、引导尺度、负面提示、数据增强、仰角范围及SDS替代方案等不同因素对生成质量的影响。