EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth
This work addresses the need for efficient and high-quality texturing in 3D modeling, offering a novel method that improves upon existing techniques, though it is incremental in its approach.
The paper tackles the problem of generating textures for 3D models from text prompts and meshes by incorporating depth information with Stable Diffusion, resulting in faster generation times and more satisfactory, stylistically diverse textures as validated by user studies on the Objaverse dataset.
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.