3D Gaussian Splatting（3DGS，三维高斯溅射）可实现高保真渲染并具备快速实时性能，但现有方法依赖于完整运动恢复结构（Structure-from-Motion, SfM）处理后的离线训练。与之不同，本研究提出Gaussian on-the-fly Splatting（简称On-the-Fly GS，即时高斯溅射），这是一种可在图像采集过程中实现近实时3DGS优化的渐进式框架。每帧图像到达时，通过On-the-Fly SfM（即时运动恢复结构）更新其位姿与稀疏点，新优化的高斯体会立即整合至3DGS场中。为实现这一目标，我们提出渐进式局部与半全局优化方法，依据对应重叠关系优先处理新图像及其邻域图像，使新图像及其重叠图像获得更多训练。为进一步稳定新旧图像间的训练，我们采用自适应学习率调度来平衡迭代次数与学习率。在多个基准上的大量实验表明，我们的On-the-Fly GS大幅缩短了训练时间，每帧新图像的优化仅需数秒且渲染损失极小，是迈向快速渐进式3DGS重建的首批实用步骤之一。
英文摘要：
3D Gaussian Splatting (3DGS) achieves high-fidelity rendering with fast real-time performance, but existing methods rely on offline training after full Structure-from-Motion (SfM) processing. In contrast, this work introduces Gaussian on-the-fly Splatting (abbreviated as On-the-Fly GS), a progressive framework enabling near real-time 3DGS optimization during image capture. As each image arrives, its pose and sparse points are updated via On-the-Fly SfM, and newly optimized Gaussians are immediately integrated into the 3DGS field. To achieve this, we propose a progressive Local & Semi-Global optimization to prioritize the new image and its neighbors by their corresponding overlapping relationship, allowing the new image and its overlapping images to get more training. To further stabilize training across previous and new images, an adaptive learning rate schedule balances the iterations and the learning rate. Extensive experiments on multiple benchmarks show that our On-the-Fly GS reduces training time significantly, optimizing each new image in seconds with minimal rendering loss, offering one of the first practical steps toward rapid, progressive 3DGS reconstruction.
Chongqing University（重庆大学）；MAIS, Institute of Automation, Chinese Academy of Sciences and UCAS（自动化研究所，中国科学院，UCAS）；King Abdullah University of Science and Technology (KAUST)（卡塔尔科学与技术大学）
GSFusion: Online RGB-D Mapping Where Gaussian Splatting Meets TSDF Fusion
Smart Robotics Lab, Technical University of Munich（慕尼黑工业大学智能机器人实验室）；Munich Institute of Robotics and Machine Intelligence (MIRMI)（慕尼黑机器人与机器智能研究所）；Smart Robotics Lab, Imperial College London（伦敦帝国理工学院智能机器人实验室）
SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
The Chinese University of Hong Kong（香港中文大学）；Hong Kong Center for Logistics Robotics（香港物流机器人中心）；University of California, Berkeley（加州大学伯克利分校）；Zhejiang University（浙江大学）
HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction
Institute for Photogrammetry and Geoinformatics, University of Stuttgart（摄影测量与地理信息学研究所，斯图加特大学）；Technical University of Munich（慕尼黑技术大学）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用科学大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）
