Customize-It-3D：使用主题特定知识先验从单个图像创建高质量3D模型

摘要

本文提出了一种新颖的两阶段方法，充分利用参考图像提供的信息，为图像到三维生成建立定制化知识先验。之前的方法主要依赖于通用扩散先验，难以与参考图像产生一致的结果，我们提出了一种主体特定和多模态扩散模型。该模型不仅通过考虑阴影模式来帮助 NeRF 优化以改善几何结构，还从粗糙结果中增强纹理以实现卓越的细化。这两个方面有助于将三维内容与主体忠实地对齐。大量实验证明了我们的方法 Custom-It-3D 的优越性，远远超过以往的工作。它生成了具有令人印象深刻视觉质量的忠实360度重建，非常适用于各种应用，包括文本到三维创建。

English

In this paper, we present a novel two-stage approach that fully utilizes the information provided by the reference image to establish a customized knowledge prior for image-to-3D generation. While previous approaches primarily rely on a general diffusion prior, which struggles to yield consistent results with the reference image, we propose a subject-specific and multi-modal diffusion model. This model not only aids NeRF optimization by considering the shading mode for improved geometry but also enhances texture from the coarse results to achieve superior refinement. Both aspects contribute to faithfully aligning the 3D content with the subject. Extensive experiments showcase the superiority of our method, Customize-It-3D, outperforming previous works by a substantial margin. It produces faithful 360-degree reconstructions with impressive visual quality, making it well-suited for various applications, including text-to-3D creation.

Customize-It-3D：使用主题特定知识先验从单个图像创建高质量3D模型

Customize-It-3D: High-Quality 3D Creation from A Single Image Using Subject-Specific Knowledge Prior

摘要

Support