三维网格的图像引导几何风格化
Image-Guided Geometric Stylization of 3D Meshes
把预训练扩散模型当作图像风格的抽象先验，配合近似 VAE 编码器从网格渲染中回传稳定梯度，再用粗到细的变形流程驱动网格顶点位移——这套「渲染-编码-引导」的可微管线可直接迁移到任何需要图像监督的三维几何优化任务（如单图建模、形状编辑）。
原文依据 we propose an approximate VAE encoder that provides efficient and reliable gradients from mesh renderings
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期的生成模型能够创建视觉上合理的三维物体表示。然而，其生成过程往往只允许隐式的控制信号（如上下文描述），并且很少支持超出既有数据分布的、大胆的几何变形。我们提出一个几何风格化框架，对三维网格进行变形，使其表达某张图像的风格。由于风格本身具有固有的歧义性，我们利用预训练的扩散模型来提取所给图像的抽象表示。我们的由粗到细的风格化流程能够对输入三维模型进行大幅变形，以表达多样化的几何变化，同时保留原始网格的有效拓扑与部件级语义。我们还提出一个近似变分自编码器编码器，它能够从网格渲染中提供高效且可靠的梯度。大量实验表明，我们的方法能够生成风格化的三维网格，这些网格反映了所描绘资产的独特几何特征，例如富有表现力的姿态与轮廓，从而支持创作独特的艺术三维作品。项目主页：https://changwoonchoi.github.io/GeoStyle
英文原文摘要 1166 字符
Recent generative models can create visually plausible 3D representations of objects. However, the generation process often allows for implicit control signals, such as contextual descriptions, and rarely supports bold geometric distortions beyond existing data distributions. We propose a geometric stylization framework that deforms a 3D mesh, allowing it to express the style of an image. While style is inherently ambiguous, we utilize pre-trained diffusion models to extract an abstract representation of the provided image. Our coarse-to-fine stylization pipeline can drastically deform the input 3D model to express a diverse range of geometric variations while retaining the valid topology of the original mesh and part-level semantics. We also propose an approximate VAE encoder that provides efficient and reliable gradients from mesh renderings. Extensive experiments demonstrate that our method can create stylized 3D meshes that reflect unique geometric features of the pictured assets, such as expressive poses and silhouettes, thereby supporting the creation of distinctive artistic 3D creations. Project page: https://changwoonchoi.github.io/GeoStyle