发表机构
School of Computer Science, Northwestern Polytechnical University; CEMSE, King Abdullah University of Science and Technology（西北工业大学计算机学院; 阿卜杜拉国王科技大学计算、电子与数学科学和工程学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对无序图像3D场景重建受SfM预处理等限制的问题，提出SalientGS统一流水线，用重要性引导的MCMC高斯分配聚合残差，实现15分钟端到端重建且质量一流，还提供相关分析及代码脚本。
AI 中文摘要
从无序图像重建3D场景仍然受到昂贵的结构光运动（SfM）预处理和固定姿态接口的限制。我们提出了SalientGS，一种统一的从SfM到3D高斯溅射（3DGS）的流水线。其核心贡献是重要性引导的马尔可夫链蒙特卡罗（MCMC）高斯分配，它将多视图残差聚合成每个高斯的欠拟合和冗余信号。这些信号定义了一个平滑的重要性加权采样分布，使出生和重新定位偏向欠拟合区域。这在不改变底层随机梯度朗之万动力学（SGLD）的情况下，从拟合良好的区域重新分配了容量。SalientGS在15分钟内实现了端到端重建，具有一流的感知质量。补充材料提供了针对每个场景的定性比较和每个图像的学习感知图像块相似性（LPIPS）分析的专用部分，包括失败案例。代码和评估脚本可在此https URL上获取。
英文摘要
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.
CommentsAccepted
