FlexiTex: Enhancing Texture Generation via Visual Guidance
This work addresses texture generation for applications like 3D modeling or graphics, but it is incremental as it builds on existing diffusion models with visual guidance enhancements.
The paper tackles the problem of blurry or inconsistent patterns in texture generation from abstract textual prompts by introducing FlexiTex, which uses visual guidance to embed rich information, resulting in high-quality textures with preserved high-frequency details and global consistency.
Recent texture generation methods achieve impressive results due to the powerful generative prior they leverage from large-scale text-to-image diffusion models. However, abstract textual prompts are limited in providing global textural or shape information, which results in the texture generation methods producing blurry or inconsistent patterns. To tackle this, we present FlexiTex, embedding rich information via visual guidance to generate a high-quality texture. The core of FlexiTex is the Visual Guidance Enhancement module, which incorporates more specific information from visual guidance to reduce ambiguity in the text prompt and preserve high-frequency details. To further enhance the visual guidance, we introduce a Direction-Aware Adaptation module that automatically designs direction prompts based on different camera poses, avoiding the Janus problem and maintaining semantically global consistency. Benefiting from the visual guidance, FlexiTex produces quantitatively and qualitatively sound results, demonstrating its potential to advance texture generation for real-world applications.