从杂乱点云直接生成艺术风格网格，无需复杂流程。
Artist-Created Mesh Generation from Raw Observation
- 将点云修复转化为2D图像补全任务，用生成模型提升质量。
- 在ShapeNet上实现干净完整的网格生成，效果优于传统方法。
- 适合需要快速生成可动画化模型的影视与游戏开发者。
我们提出一种端到端框架，可从噪声或不完整的点云（如LiDAR或移动RGB-D相机捕获）中生成艺术家风格的网格。艺术风格网格对商业图形管线至关重要，因其兼容动画与贴图工具且渲染效率高。然而现有方法通常假设输入为干净完整数据，或依赖复杂的多阶段流程，难以适用于真实场景。为此，我们提出一种端到端方法，直接对输入点云进行精炼并生成高质量艺术家风格网格。核心在于将3D点云修复重新构想为2D图像补全任务，从而利用强大的生成模型。在ShapeNet数据集上的初步结果表明，该框架在生成干净、完整的网格方面展现出显著潜力。
原文摘要 · Abstract (English)
We present an end-to-end framework for generating artist-style meshes from noisy or incomplete point clouds, such as those captured by real-world sensors like LiDAR or mobile RGB-D cameras. Artist-created meshes are crucial for commercial graphics pipelines due to their compatibility with animation and texturing tools and their efficiency in rendering. However, existing approaches often assume clean, complete inputs or rely on complex multi-stage pipelines, limiting their applicability in real-world scenarios. To address this, we propose an end-to-end method that refines the input point cloud and directly produces high-quality, artist-style meshes. At the core of our approach is a novel reformulation of 3D point cloud refinement as a 2D inpainting task, enabling the use of powerful generative models. Preliminary results on the ShapeNet dataset demonstrate the promise of our framework in producing clean, complete meshes.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。