Yiwei Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yiwei Xu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Hao Cheng
University of Twente
1 shared publication - Tengfei Wang
Wuhan University
1 shared publication Wentian Gan
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
1 shared publication- Xin Wang
Wuhan University
1 shared publication - Yifei Yu
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
1 shared publication - Zongqian Zhan
Wuhan University
1 shared publication
Latest Publications
- 14 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (1) , 426-433
Gaussian On-the-Fly Splatting: A Progressive Framework for Robust Near Real-Time 3DGS Optimization
3D Gaussian Splatting (3DGS) achieves high-fidelity rendering with 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 Zhan et al., 2025, and newly optimized Gaussians are immediately integrated into the already existed 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.
- 14 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (1) , 426-433
Gaussian On-the-Fly Splatting: A Progressive Framework for Robust Near Real-Time 3DGS Optimization
3D Gaussian Splatting (3DGS) achieves high-fidelity rendering with 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 Zhan et al., 2025, and newly optimized Gaussians are immediately integrated into the already existed 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.