用可见性图提升稀疏视角合成，让模糊区域更清晰
CoMapGS: Covisibility Map-based Gaussian Splatting for Sparse Novel View Synthesis
- 用可见性图定位模糊和高不确定区域，针对性优化重建
- 改进初始点云，使稀疏数据下3D高斯点阵更完整
- 自适应加权训练，适配不同稀疏程度的场景
我们提出基于可见性图的高斯点绘（CoMapGS），用于恢复稀疏视角合成中欠代表区域。CoMapGS通过构建可见性图，同时处理高不确定性与低不确定性区域，增强初始点云，并利用邻近分类器实现不确定性感知的加权监督。贡献有三：(1) 将可见性图作为核心组件重构新视角合成任务，解决区域特异性不确定性；(2) 对高低不确定性区域均优化初始点云，弥补稀疏COLMAP点云缺陷，提升重建质量，尤其利于少样本3DGS方法；(3) 基于可见性得分加权与邻近分类的自适应监督，在不同稀疏度场景下实现稳定性能提升。实验表明，CoMapGS在Mip-NeRF 360与LLFF等数据集上优于现有最佳方法。
原文摘要 · Abstract (English)
We propose Covisibility Map-based Gaussian Splatting (CoMapGS), designed to recover underrepresented sparse regions in sparse novel view synthesis. CoMapGS addresses both high- and low-uncertainty regions by constructing covisibility maps, enhancing initial point clouds, and applying uncertainty-aware weighted supervision using a proximity classifier. Our contributions are threefold: (1) CoMapGS reframes novel view synthesis by leveraging covisibility maps as a core component to address region-specific uncertainty; (2) Enhanced initial point clouds for both low- and high-uncertainty regions compensate for sparse COLMAP-derived point clouds, improving reconstruction quality and benefiting few-shot 3DGS methods; (3) Adaptive supervision with covisibility-score-based weighting and proximity classification achieves consistent performance gains across scenes with varying sparsity scores derived from covisibility maps. Experimental results demonstrate that CoMapGS outperforms state-of-the-art methods on datasets including Mip-NeRF 360 and LLFF.
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。