用可微高斯点阵代替硬投影，让3D点云补全更好利用视觉信息。
SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
- 用可微高斯点阵实现连续密度估计，替代传统稀疏硬投影
- 在PCN、ShapeNet和KITTI上均达当前最优性能
- 实证证明方法真正建立跨模态连接，不依赖视觉时仍有效
尽管多模态学习推动了点云补全的发展，但其理论机制仍不清晰。现有方法归因于模态间关联，但我们发现标准硬投影会切断这种关联：将稀疏点云投影到图像平面会产生极稀疏的支持区域，阻碍视觉先验传播，这一失效模式称为跨模态熵坍缩。为解决此问题，我们提出SplAttN，以可微高斯点阵替代硬投影，生成稠密连续的图像平面表征。通过将投影重定义为连续密度估计，SplAttN避免了稀疏支持的坍缩，促进梯度流动，提升跨模态连接的学习能力。大量实验表明，SplAttN在PCN和ShapeNet-55/34上达到当前最优表现。关键的是，我们采用真实世界KITTI基准作为多模态依赖性的压力测试。反事实评估显示，基线方法在移除视觉信息后退化为仅依赖模板的单模态检索器，而SplAttN仍保持对视觉线索的稳健依赖，验证了本方法建立了有效的跨模态连接。代码已开源。
原文摘要 · Abstract (English)
Although multi-modal learning has advanced point cloud completion, the theoretical mechanisms remain unclear. Recent works attribute success to the connection between modalities, yet we identify that standard hard projection severs this connection: projecting a sparse point cloud onto the image plane yields an extremely sparse support, which hinders visual prior propagation, a failure mode we term Cross-Modal Entropy Collapse. To address this practical limitation, we propose SplAttN, which replaces hard projection with Differentiable Gaussian Splatting to produce a dense, continuous image-plane representation. By reformulating projection as continuous density estimation, SplAttN avoids collapsed sparse support, facilitates gradient flow, and improves cross-modal connection learnability. Extensive experiments show that SplAttN achieves state-of-the-art performance on PCN and ShapeNet-55/34. Crucially, we utilize the real-world KITTI benchmark as a stress test for multi-modal reliance. Counter-factual evaluation reveals that while baselines degenerate into unimodal template retrievers insensitive to visual removal, SplAttN maintains a robust dependency on visual cues, validating that our method establishes an effective cross-modal connection. Code is available at https://github.com/zay002/SplAttN.
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。