用透明度梯度优化3D高斯点云，让少样本重建更紧凑高效
Opacity-Gradient Driven Density Control for Compact and Efficient Few-Shot 3D Gaussian Splatting
- 以透明度梯度替代位置梯度，作为新增点的触发依据
- 在LLFF数据集上仅需32k点，比FSGS减少40%以上
- 适合追求高效率的少样本3D重建应用
3D高斯点云（3DGS）在少样本场景下常因标准自适应密度控制导致过拟合和模型膨胀。现有方法如FSGS虽提升质量，但显著增加点数。本文提出新框架，重构3DGS优化机制以提升效率。将传统的位置梯度启发式替换为基于透明度梯度的轻量级渲染误差代理，作为新增点的触发条件。研究发现，这种激进的加密策略需搭配更保守的删除机制，才能避免破坏性优化循环。结合标准深度相关性损失进行几何引导，显著提升效率。在3视图LLFF数据集上，模型点数仅32k（FSGS为57k），压缩超40%；在Mip-NeRF 360上点数减少约70%。该性能提升以微小的质量代价实现，确立了少样本视角合成中质量与效率的新前沿。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) struggles in few-shot scenarios, where its standard adaptive density control (ADC) can lead to overfitting and bloated reconstructions. While state-of-the-art methods like FSGS improve quality, they often do so by significantly increasing the primitive count. This paper presents a framework that revises the core 3DGS optimization to prioritize efficiency. We replace the standard positional gradient heuristic with a novel densification trigger that uses the opacity gradient as a lightweight proxy for rendering error. We find this aggressive densification is only effective when paired with a more conservative pruning schedule, which prevents destructive optimization cycles. Combined with a standard depth-correlation loss for geometric guidance, our framework demonstrates a fundamental improvement in efficiency. On the 3-view LLFF dataset, our model is over 40% more compact (32k vs. 57k primitives) than FSGS, and on the Mip-NeRF 360 dataset, it achieves a reduction of approximately 70%. This dramatic gain in compactness is achieved with a modest trade-off in reconstruction metrics, establishing a new state-of-the-art on the quality-vs-efficiency Pareto frontier for few-shot view synthesis.
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。