EucliDreamer: Fast and High-Quality Texturing for 3D Models with Depth-Conditioned Stable Diffusion
Preprint
Abstract
We present EucliDreamer, a simple and effective method to generate textures for 3D models given text prompts and meshes. The texture is parametrized as an implicit function on the 3D surface, which is optimized with the Score Distillation Sampling (SDS) process and differentiable rendering. To generate high-quality textures, we leverage a depth-conditioned Stable Diffusion model guided by the depth image rendered from the mesh. We test our approach on 3D models in Objaverse and conducted a user study, which shows its superior quality compared to existing texturing methods like Text2Tex. In addition, our method converges 2 times faster than DreamFusion. Through text prompting, textures of diverse art styles can be produced. We hope Euclidreamer proides a viable solution to automate a labor-intensive stage in 3D content creation.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Segment Anything Model for Road Network Graph Extraction2024
- Synthetic Datasets for Autonomous Driving: A SurveyIEEE Transactions on Intelligent Vehicles, 2023
- Adding Conditional Control to Text-to-Image Diffusion Models2023
- Delta Denoising Score2023
- Vox-E: Text-guided Voxel Editing of 3D Objects2023
- Text2Tex: Text-driven Texture Synthesis via Diffusion Models2023
- Unlocking Everyday Wisdom: Enhancing Machine Comprehension with Script Knowledge IntegrationApplied Sciences, 2023
- Instant neural graphics primitives with a multiresolution hash encodingACM Transactions on Graphics, 2022
- Modular primitives for high-performance differentiable renderingACM Transactions on Graphics, 2020
- Real-time shading-based refinement for consumer depth camerasACM Transactions on Graphics, 2014