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 [28] with depth conditional Stable Diffusion [34]. We ran our model over the open-source dataset Objaverse [7] 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：本文提出了一种新方法，可根据文本提示和三维网格为3D模型生成纹理。通过引入额外深度信息，结合深度条件稳定扩散模型[34]执行分数蒸馏采样（SDS）过程[28]。我们在开源数据集Objaverse[7]上运行模型，并通过用户研究将结果与多种3D纹理生成方法进行对比。实验表明，本模型不仅能生成更令人满意的结果，还能为同一物体呈现多种艺术风格。此外，在生成同等质量纹理时，我们实现了更快的处理速度。我们还通过全面消融实验分析了可能影响生成质量的不同因素，包括采样步数、引导尺度、否定提示、数据增强、仰角范围及SDS替代方案。