用张量投票增强稀疏视角下的3D高斯点云几何结构
TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse views
- 通过张量投票实现高斯点间直接通信，提升几何一致性
- 在DTU和Tanks-and-Temples上稀疏视图下重建精度显著提升
- 无需渲染即可计算3D损失，兼容多种模型架构
高斯点云在新视角合成中表现优异，但点间仅通过投影像素间接交互。本文提出TV-SGS，引入张量投票机制，在测试优化阶段直接促进点云间的几何信息传播，增强3D结构。设计了一类不依赖渲染的新型3D损失，可与现有损失无缝结合，尤其在输入视角稀疏、图像监督有限时效果更优。方法适用于多种主干网络，在DTU和Tanks-and-Temples数据集上的实验表明，相较基线模型，其几何重建质量明显提升，同时保持或改善了渲染效果。
原文摘要 · Abstract (English)
Gaussian Splatting has been effective in inferring scene representations that excel in novel view synthesis. Multiple splats cooperate seamlessly to synthesize the pixels of novel views and are jointly optimized even though they only affect each other indirectly, via pixels they project to in common. We present an approach that enables direct communication among splats to enhance the geometric structures they form in 3D. This is accomplished by Tensor Voting, which was originally designed to infer structures from noisy inputs and has been adapted here to provide supervision during test-time optimization, leading to more accurate scene geometry. We introduce a new class of 3D losses that do not rely on rendering and can be combined with essentially all losses previously reported in the literature. Our 3D losses are especially effective when the input views are sparse and geometric regularization is essential due to limited supervision from the images. Our method is easy to integrate with a diverse set of backbones, and our experiments on the DTU and Tanks-and-Temples datasets demonstrate that TV-SGS improves the geometry of the outputs compared to the backbone, while maintaining or improving rendering quality.
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。