RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis

• URL: http://arxiv.org/abs/2503.19011v1
• Date: Mon, 24 Mar 2025 17:56:11 GMT
• Title: RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis
• Authors: Yifei Feng, Mingxin Yang, Shuhui Yang, Sheng Zhang, Jiaao Yu, Zibo Zhao, Yuhong Liu, Jie Jiang, Chunchao Guo,
• Abstract summary: RomanTex is a multiview-based texture generation framework that integrates a multi-attention network with an underlying 3D representation.<n>Our method achieves state-of-the-art results in texture quality and consistency.
• Score: 10.350576861948952
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Painting textures for existing geometries is a critical yet labor-intensive process in 3D asset generation. Recent advancements in text-to-image (T2I) models have led to significant progress in texture generation. Most existing research approaches this task by first generating images in 2D spaces using image diffusion models, followed by a texture baking process to achieve UV texture. However, these methods often struggle to produce high-quality textures due to inconsistencies among the generated multi-view images, resulting in seams and ghosting artifacts. In contrast, 3D-based texture synthesis methods aim to address these inconsistencies, but they often neglect 2D diffusion model priors, making them challenging to apply to real-world objects To overcome these limitations, we propose RomanTex, a multiview-based texture generation framework that integrates a multi-attention network with an underlying 3D representation, facilitated by our novel 3D-aware Rotary Positional Embedding. Additionally, we incorporate a decoupling characteristic in the multi-attention block to enhance the model's robustness in image-to-texture task, enabling semantically-correct back-view synthesis. Furthermore, we introduce a geometry-related Classifier-Free Guidance (CFG) mechanism to further improve the alignment with both geometries and images. Quantitative and qualitative evaluations, along with comprehensive user studies, demonstrate that our method achieves state-of-the-art results in texture quality and consistency.

Related papers

• Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation [56.862552362223425]
  This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts.<n>The framework consists of 3D shape generation and texture generation.<n>This report details the system architecture, experimental results, and potential future directions to improve and expand the framework.
  arXiv  Detail & Related papers  (2025-02-20T04:22:30Z)
• InsTex: Indoor Scenes Stylized Texture Synthesis [81.12010726769768]
  High-quality textures are crucial for 3D scenes for augmented/virtual reality (ARVR) applications.<n>Current methods suffer from lengthy processing times and visual artifacts.<n>We introduce two-stage architecture designed to generate high-quality textures for 3D scenes.
  arXiv  Detail & Related papers  (2025-01-22T08:37:59Z)
• GenesisTex2: Stable, Consistent and High-Quality Text-to-Texture Generation [35.04723374116026]
  Large-scale text-to-image (T2I) models have shown astonishing results in text-to-image (T2I) generation. 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. We propose a novel text-to-texture synthesis framework that leverages pretrained diffusion models.
  arXiv  Detail & Related papers  (2024-09-27T02:32:42Z)
• VCD-Texture: Variance Alignment based 3D-2D Co-Denoising for Text-Guided Texturing [22.39760469467524]
  We propose a Variance texture synthesis to address the modal gap between the 2D and 3D diffusion models. We present an inpainting module to improve details with conflicting regions.
  arXiv  Detail & Related papers  (2024-07-05T12:11:33Z)
• Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects [54.80813150893719]
  We introduce Meta 3D TextureGen: a new feedforward method comprised of two sequential networks aimed at generating high-quality textures in less than 20 seconds. Our method state-of-the-art results in quality and speed by conditioning a text-to-image model on 3D semantics in 2D space and fusing them into a complete and high-resolution UV texture map. In addition, we introduce a texture enhancement network that is capable of up-scaling any texture by an arbitrary ratio, producing 4k pixel resolution textures.
  arXiv  Detail & Related papers  (2024-07-02T17:04:34Z)
• TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models [77.85129451435704]
  We present a new method to synthesize textures for 3D, using large-scale-guided image diffusion models. Specifically, we leverage latent diffusion models, apply the set denoising model and aggregate denoising text map.
  arXiv  Detail & Related papers  (2023-10-20T19:15:29Z)
• Guide3D: Create 3D Avatars from Text and Image Guidance [55.71306021041785]
  Guide3D is a text-and-image-guided generative model for 3D avatar generation based on diffusion models. Our framework produces topologically and structurally correct geometry and high-resolution textures.
  arXiv  Detail & Related papers  (2023-08-18T17:55:47Z)
• TEXTure: Text-Guided Texturing of 3D Shapes [71.13116133846084]
  We present TEXTure, a novel method for text-guided editing, editing, and transfer of textures for 3D shapes. We define a trimap partitioning process that generates seamless 3D textures without requiring explicit surface textures.
  arXiv  Detail & Related papers  (2023-02-03T13:18:45Z)
• Fine Detailed Texture Learning for 3D Meshes with Generative Models [33.42114674602613]
  This paper presents a method to reconstruct high-quality textured 3D models from both multi-view and single-view images. In the first stage, we focus on learning accurate geometry, whereas in the second stage, we focus on learning the texture with a generative adversarial network. We demonstrate that our method achieves superior 3D textured models compared to the previous works.
  arXiv  Detail & Related papers  (2022-03-17T14:50:52Z)
• Unsupervised High-Fidelity Facial Texture Generation and Reconstruction [20.447635896077454]
  We propose a novel unified pipeline for both tasks, generation of both geometry and texture, and recovery of high-fidelity texture. Our texture model is learned, in an unsupervised fashion, from natural images as opposed to scanned texture maps. By applying precise 3DMM fitting, we can seamlessly integrate our modeled textures into synthetically generated background images.
  arXiv  Detail & Related papers  (2021-10-10T10:59:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.