无需迭代去噪，3D点云生成一步到位，速度快质量高。
A Continuous-Time Consistency Model for 3D Point Cloud Generation
- 用连续时间模型直接在点空间生成，跳过传统扩散步骤。
- 单步生成即达高保真度，比现有方法更快更准。
- 适合需要快速生成高质量3D模型的机器人与VR应用。
快速准确地从点云生成3D形状在机器人、增强现实/虚拟现实（AR/VR）和数字内容创作中至关重要。我们提出ConTiCoM-3D，一种在点空间中直接合成3D形状的连续时间一致性模型，无需离散化扩散步骤、预训练教师模型或潜在空间编码。该方法融合受TrigFlow启发的连续噪声调度与基于Chamfer Distance的几何损失，支持在高维点集上稳定训练，并避免昂贵的雅可比向量乘积。此设计实现高效的一至两步推理，具有高几何保真度。与依赖迭代去噪或潜在解码器的先前方法不同，ConTiCoM-3D采用完全在连续时间运行的时间条件神经网络，从而实现快速生成。在ShapeNet基准上的实验表明，ConTiCoM-3D在质量和效率方面均达到或超越当前最先进的扩散模型和潜在一致性模型，确立了其作为可扩展3D形状生成实用框架的地位。
原文摘要 · Abstract (English)
Fast and accurate 3D shape generation from point clouds is essential for applications in robotics, AR/VR, and digital content creation. We introduce ConTiCoM-3D, a continuous-time consistency model that synthesizes 3D shapes directly in point space, without discretized diffusion steps, pre-trained teacher models, or latent-space encodings. The method integrates a TrigFlow-inspired continuous noise schedule with a Chamfer Distance-based geometric loss, enabling stable training on high-dimensional point sets while avoiding expensive Jacobian-vector products. This design supports efficient one- to two-step inference with high geometric fidelity. In contrast to previous approaches that rely on iterative denoising or latent decoders, ConTiCoM-3D employs a time-conditioned neural network operating entirely in continuous time, thereby achieving fast generation. Experiments on the ShapeNet benchmark show that ConTiCoM-3D matches or outperforms state-of-the-art diffusion and latent consistency models in both quality and efficiency, establishing it as a practical framework for scalable 3D shape generation.
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。