用概率掩码动态管理3D高斯点，减少内存占用同时保持高质量渲染。
MaskGaussian: Adaptive 3D Gaussian Representation from Probabilistic Masks
- 将高斯点视为概率实体，不直接删除，而是按存在概率动态管理。
- 平均剪枝超60%的高斯点，仅损失0.02 dB PSNR，优于传统方法。
- 适合追求高效实时渲染与低内存占用的3D重建应用。
尽管3D高斯溅射（3DGS）在新视角合成与实时渲染中表现优异，但数百万个高斯点带来的高内存消耗限制了其实际应用。现有改进通过手工规则或学习掩码剪枝冗余点，但这些方法基于剪枝时刻的静态快照，导致长期重建性能不佳。为此，我们提出MaskGaussian，将高斯点建模为概率实体，根据其存在概率动态使用。为此，我们设计了一种掩码光栅化技术，使未被使用但具有概率存在的高斯点仍可接收梯度，从而动态评估其对场景演化的贡献，并调整其存在概率。因此，高斯点的重要性随时间迭代变化，剪枝选择更具多样性。大量实验表明，该方法在使用更少高斯点的情况下，渲染质量优于以往剪枝方法：平均剪枝超过60%，仅导致0.02 dB PSNR下降。代码见：https://github.com/kaikai23/MaskGaussian。
原文摘要 · Abstract (English)
While 3D Gaussian Splatting (3DGS) has demonstrated remarkable performance in novel view synthesis and real-time rendering, the high memory consumption due to the use of millions of Gaussians limits its practicality. To mitigate this issue, improvements have been made by pruning unnecessary Gaussians, either through a hand-crafted criterion or by using learned masks. However, these methods deterministically remove Gaussians based on a snapshot of the pruning moment, leading to sub-optimized reconstruction performance from a long-term perspective. To address this issue, we introduce MaskGaussian, which models Gaussians as probabilistic entities rather than permanently removing them, and utilize them according to their probability of existence. To achieve this, we propose a masked-rasterization technique that enables unused yet probabilistically existing Gaussians to receive gradients, allowing for dynamic assessment of their contribution to the evolving scene and adjustment of their probability of existence. Hence, the importance of Gaussians iteratively changes and the pruned Gaussians are selected diversely. Extensive experiments demonstrate the superiority of the proposed method in achieving better rendering quality with fewer Gaussians than previous pruning methods, pruning over 60% of Gaussians on average with only a 0.02 PSNR decline. Our code can be found at: https://github.com/kaikai23/MaskGaussian
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。