EucliDreamer: Fast and High-Quality Texturing for 3D Models with Stable Diffusion Depth

TL;DR

EucliDreamer introduces a fast, high-quality 3D texturing method using depth-aware Stable Diffusion, outperforming existing techniques in quality, style diversity, and speed, validated through extensive experiments and user studies.

Contribution

The paper proposes a novel depth-conditioned SDS approach for 3D texturing that enhances quality, diversity, and speed over prior methods.

Findings

Produces more satisfactory textures with diverse art styles.

Achieves faster texture generation with comparable quality.

Demonstrates robustness through comprehensive ablation studies.

Abstract

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.