Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913977769918464 |
|---|---|
| author | Zhao, Linqing Xu, Xiuwei Wang, Yirui Wang, Hao Zheng, Wenzhao Tang, Yansong Yan, Haibin Lu, Jiwen |
| author_facet | Zhao, Linqing Xu, Xiuwei Wang, Yirui Wang, Hao Zheng, Wenzhao Tang, Yansong Yan, Haibin Lu, Jiwen |
| contents | Incrementally recovering real-sized 3D geometry from a pose-free RGB stream is a challenging task in 3D reconstruction, requiring minimal assumptions on input data. Existing methods can be broadly categorized into end-to-end and visual SLAM-based approaches, both of which either struggle with long sequences or depend on slow test-time optimization and depth sensors. To address this, we first integrate a depth estimator into an RGB-D SLAM system, but this approach is hindered by inaccurate geometric details in predicted depth. Through further investigation, we find that 3D Gaussian mapping can effectively solve this problem. Building on this, we propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module to directly infer camera pose from optical flow. This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed. Additionally, we introduce a local graph rendering technique to enhance robustness in feed-forward pose prediction. Experimental results on the Replica and TUM-RGBD datasets, along with a real-world deployment demonstration, show that our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90\%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_04597 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline Zhao, Linqing Xu, Xiuwei Wang, Yirui Wang, Hao Zheng, Wenzhao Tang, Yansong Yan, Haibin Lu, Jiwen Computer Vision and Pattern Recognition Incrementally recovering real-sized 3D geometry from a pose-free RGB stream is a challenging task in 3D reconstruction, requiring minimal assumptions on input data. Existing methods can be broadly categorized into end-to-end and visual SLAM-based approaches, both of which either struggle with long sequences or depend on slow test-time optimization and depth sensors. To address this, we first integrate a depth estimator into an RGB-D SLAM system, but this approach is hindered by inaccurate geometric details in predicted depth. Through further investigation, we find that 3D Gaussian mapping can effectively solve this problem. Building on this, we propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module to directly infer camera pose from optical flow. This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed. Additionally, we introduce a local graph rendering technique to enhance robustness in feed-forward pose prediction. Experimental results on the Replica and TUM-RGBD datasets, along with a real-world deployment demonstration, show that our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90\%. |
| title | Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.04597 |