| | --- |
| | pipeline_tag: robotics |
| | tags: |
| | - RGB-D SLAM |
| | - dense-reconstruction |
| | - camera-tracking |
| | --- |
| | |
| | # PROFusion: Robust and Accurate Dense Reconstruction via Camera Pose Regression and Optimization |
| |
|
| | [ICRA 2026] PROFusion is a simple yet effective system for real-time camera tracking and dense scene reconstruction, providing both robustness against unstable camera motions and accurate reconstruction results. |
| |
|
| | This repository contains pre-trained weights for the **pose regression module**, which estimates the relative camera pose (in metric-scale) between two RGB-D frames. |
| |
|
| | - **Paper:** [PROFusion: Robust and Accurate Dense Reconstruction via Camera Pose Regression and Optimization](https://arxiv.org/abs/2509.24236) |
| | - **Code:** [GitHub Repository](https://github.com/siyandong/PROFusion) |
| |
|
| | ## Method Overview |
| |
|
| | Real-time dense scene reconstruction during unstable camera motions is crucial for robotics, yet current RGB-D SLAM systems often fail when cameras experience large viewpoint changes, fast motions, or sudden shaking. PROFusion addresses this challenge through a combination of learning-based initialization with optimization-based refinement. |
| |
|
| | The system employs a camera pose regression network to predict metric-aware relative poses from consecutive RGB-D frames, which serve as reliable starting points for a randomized optimization algorithm that further aligns depth images with the scene geometry. The system operates in real-time, showcasing that combining simple and principled techniques can achieve both robustness for unstable motions and accuracy for dense reconstruction. |
| |
|
| | ## Citation |
| |
|
| | If you find this work helpful in your research, please consider citing: |
| |
|
| | ```bibtex |
| | @article{dong2025profusion, |
| | title={PROFusion: Robust and Accurate Dense Reconstruction via Camera Pose Regression and Optimization}, |
| | author={Dong, Siyan and Wang, Zijun and Cai, Lulu and Ma, Yi and Yang, Yanchao}, |
| | journal={arXiv preprint arXiv:2509.24236}, |
| | year={2025} |
| | } |
| | ``` |
| |
|
| | ## Acknowledgments |
| |
|
| | The implementation is based on several inspiring works in the community, including [DUSt3R](https://github.com/naver/dust3r), [SLAM3R](https://github.com/PKU-VCL-3DV/SLAM3R), [Reloc3r](https://github.com/ffrivera0/reloc3r), and [ROSEFusion](https://github.com/jzhzhang/ROSEFusion). |
