用误差指导自适应分裂，让3D高斯点云更快发现细节结构。
AdpSplit: Error-Driven Adaptive Splitting for Faster Geometry Discovery in 3D Gaussian Splatting
- 根据像素误差统计动态决定分裂数量和参数初始化
- 在多个数据集上减少9.2%-22.3%训练时间
- 适合追求高效训练的3D重建研究者
3D高斯点云（3DGS）中的自适应密度控制通过固定数量的随机二分分裂不断增长高斯分布以发现场景结构。然而，在原始3DGS中，其二分分裂操作需要大量精炼轮次才能展现精细细节，成为少迭代训练方案的瓶颈。本文提出AdpSplit，一种基于误差驱动的自适应分裂算子，根据L1像素误差区域统计确定分裂子节点数量并初始化参数，从而减少精炼迭代次数，降低训练时间，同时保持全训练周期的渲染质量。在MipNeRF360、Deep-Blending和Tanks&Temples数据集上，AdpSplit作为标准分裂算子的即插即用替代品，使多个加速3DGS流水线的训练时间减少9.2%–22.3%。在FastGS框架下，AdpSplit在MipNeRF360上达到全周期PSNR水平，训练时间减少16.4%，相较原始3DGS实现12.6倍加速。
原文摘要 · Abstract (English)
Adaptive density control in 3D Gaussian Splatting (3DGS) repeatedly grows the Gaussian population through fixed-cardinality random splitting to discover useful scene structure. However, in vanilla 3DGS, its binary split operator requires many densification rounds to expose fine details, making it a bottleneck for efficient training schedules with fewer iterations. We introduce AdpSplit, an error-driven adaptive split operator that determines the number of split children and initializes the child parameters from L1-pixel-error region statistics, enabling fewer densification iterations, thus reduced training time, while preserving the rendering quality of full-schedule training. Across the MipNeRF360, Deep-Blending, and Tanks&Temples datasets, AdpSplit reduces the training time of multiple accelerated 3DGS pipelines by 9.2%-22.3% as a simple drop-in replacement for the standard split operator. With FastGS, AdpSplit matches the full-schedule PSNR on MipNeRF360 while reducing training time by 16.4%, corresponding to a 12.6x acceleration over vanilla 3DGS.
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。