用扩散模型精修点云细节，兼顾全局一致与局部清晰。
SUMI: Scalable Unified Model for 3D Point Cloud Inference
- 将噪声特征注入交叉注意力，实现逆向去噪精修
- 在PCN、ShapeNet等数据集上显著降低几何误差（最高降16.1%）
- 可插拔集成到现有模型，适合需要高精度点云重建的场景
点云补全通常采用从粗到精的范式，先预测低密度粗糙形状，再上采样至目标分辨率。尽管近期方法提升了整体结构恢复能力，但精细阶段常受限于简单的上采样和与粗略结构特征的交互不足，导致局部细节重建困难。本文提出SUMI，一种基于扩散模型的精修模块，用于从粗到精的点云补全。不同于以往将扩散模型作为独立生成器的方法，SUMI将噪声几何特征注入与粗结构特征的交叉注意力中，实现逆向去噪以优化局部几何，同时保持全局一致性。SUMI可灵活集成至现有从粗到精模型中作为精修模块。在PCN、ShapeNet-55/34和MVP上的实验表明，其性能持续优于强基线。SUMI在PCN上取得最优的CD和F1分数，在ShapeNet-55上最多降低16.1%的CD，且在MVP所有输出密度下均达到最佳CD表现。
原文摘要 · Abstract (English)
Point cloud completion commonly follows a coarse-to-fine paradigm, where a low-density coarse shape is first predicted and then upsampled to the target resolution. Although recent methods have improved global structure recovery, the fine stage often remains limited by simple upsampling and insufficient interaction with coarse structural features, making local detail reconstruction challenging. We propose SUMI, a diffusion-enhanced refinement module for coarse-to-fine point cloud completion. Unlike prior diffusion-based completion methods that use diffusion as a standalone point generator, SUMI injects noisy geometric features into cross-attention with coarse structural features, enabling reverse denoising to refine local geometry while preserving global consistency. SUMI can also be integrated into existing coarse-to-fine models as a flexible refinement module. Experiments on PCN, ShapeNet-55/34, and MVP demonstrate consistent improvements over strong baselines. SUMI achieves the best overall CD and F1-score on PCN, reduces CD by up to 16.1% on ShapeNet-55, and obtains the best CD across all output densities on MVP.
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。