GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation
Jiawei Lu, Yingpeng Zhang, Zengjun Zhao, He Wang, Kun Zhou, Tianjia, Shao

TL;DR
GenesisTex2 introduces a novel, efficient text-to-texture synthesis framework leveraging pretrained diffusion models, enhancing local detail and cross-view consistency without additional training, outperforming existing methods in quality and speed.
Contribution
The paper presents a new framework that improves texture consistency and detail in text-to-texture generation using local attention reweighing and latent space merging, without extra training.
Findings
Outperforms state-of-the-art in texture consistency and visual quality
Faster than distillation-based methods
Does not require additional training or fine-tuning
Abstract
Large-scale text-guided image diffusion models have shown astonishing results in text-to-image (T2I) generation. However, applying these models to synthesize textures for 3D geometries remains challenging due to the domain gap between 2D images and textures on a 3D surface. Early works that used a projecting-and-inpainting approach managed to preserve generation diversity but often resulted in noticeable artifacts and style inconsistencies. While recent methods have attempted to address these inconsistencies, they often introduce other issues, such as blurring, over-saturation, or over-smoothing. To overcome these challenges, we propose a novel text-to-texture synthesis framework that leverages pretrained diffusion models. We first introduce a local attention reweighing mechanism in the self-attention layers to guide the model in concentrating on spatial-correlated patches across…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsNatural Language Processing Techniques · Handwritten Text Recognition Techniques · Topic Modeling
MethodsSoftmax · Attention Is All You Need · Diffusion
