FlexiTex: Enhancing Texture Generation via Visual Guidance

TL;DR

FlexiTex improves texture generation by integrating visual guidance and direction-aware adaptation to produce clearer, more consistent textures from limited textual prompts, advancing the quality of generative models.

Contribution

The paper introduces FlexiTex, a novel method that enhances texture generation by embedding visual guidance and adaptive direction prompts to improve detail and consistency.

Findings

Produces higher quality textures both quantitatively and qualitatively.

Effectively reduces ambiguity and preserves high-frequency details.

Maintains global semantic consistency across different camera poses.

Abstract

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.