用重要性引导的采样方法，15分钟完成高质量3D高斯点云重建。
SalientGS: Unified SfM-to-3DGS with Importance-Guided MCMC Gaussian Allocation
- 通过马尔可夫链蒙特卡洛方法，动态分配高斯点以优化分布。
- 在15分钟内实现端到端重建，感知质量达当前最优水平。
- 适合需要快速高精度3D重建的研究者与工业应用者。
从无序图像重建3D场景仍受限于昂贵的SfM预处理和固定的位姿接口。我们提出SalientGS，一种统一的SfM到3D高斯溅射（3DGS）流程。其核心贡献是重要性引导的马尔可夫链蒙特卡洛（MCMC）高斯分配机制，将多视角残差聚合为每个高斯点的拟合不足与冗余信号。这些信号定义了一个平滑的重要性加权采样分布，使新生与重定位更偏向拟合不足区域，同时不改变底层随机梯度朗之万动力学（SGLD）。SalientGS在15分钟内实现端到端重建，达到当前最优的感知质量。补充材料包含逐场景定性对比与逐图像学习感知图像块相似性（LPIPS）分析，含失败案例。代码与评估脚本见https://github.com/Six-Bit-TX/SalientGS。
原文摘要 · Abstract (English)
Reconstructing 3D scenes from unordered images remains bottlenecked by expensive Structure-from-Motion (SfM) preprocessing and frozen pose interfaces. We present SalientGS, a unified SfM-to-3D Gaussian Splatting (3DGS) pipeline. Its central contribution is importance-guided Markov Chain Monte Carlo (MCMC) Gaussian allocation, which aggregates multi-view residuals into per-Gaussian underfit and redundancy signals. These signals define a smooth importance-weighted sampling distribution that biases both birth and relocation toward underfit regions. This reallocates capacity from well-fit areas without altering the underlying stochastic gradient Langevin dynamics (SGLD). SalientGS achieves end-to-end reconstruction in 15 minutes with state-of-the-art perceptual quality. The supplementary material provides dedicated sections for Per-Scene Qualitative Comparisons and Per-Image Learned Perceptual Image Patch Similarity (LPIPS) Analysis, including failure cases. Code and evaluation scripts are available at https://github.com/Six-Bit-TX/SalientGS.
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。