Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.17864 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911168537296896 |
|---|---|
| author | Chen, Shi Sandström, Erik Lombardi, Sandro Li, Siyuan Oswald, Martin R. |
| author_facet | Chen, Shi Sandström, Erik Lombardi, Sandro Li, Siyuan Oswald, Martin R. |
| contents | Achieving truly practical dynamic 3D reconstruction requires online operation, global pose and map consistency, detailed appearance modeling, and the flexibility to handle both RGB and RGB-D inputs. However, existing SLAM methods typically merely remove the dynamic parts or require RGB-D input, while offline methods are not scalable to long video sequences, and current transformer-based feedforward methods lack global consistency and appearance details. To this end, we achieve online dynamic scene reconstruction by disentangling the static and dynamic parts within a SLAM system. The poses are tracked robustly with a novel motion masking strategy, and dynamic parts are reconstructed leveraging a progressive adaptation of a Motion Scaffolds graph. Our method yields novel view renderings competitive to offline methods and achieves on-par tracking with state-of-the-art dynamic SLAM methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17864 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos Chen, Shi Sandström, Erik Lombardi, Sandro Li, Siyuan Oswald, Martin R. Computer Vision and Pattern Recognition Achieving truly practical dynamic 3D reconstruction requires online operation, global pose and map consistency, detailed appearance modeling, and the flexibility to handle both RGB and RGB-D inputs. However, existing SLAM methods typically merely remove the dynamic parts or require RGB-D input, while offline methods are not scalable to long video sequences, and current transformer-based feedforward methods lack global consistency and appearance details. To this end, we achieve online dynamic scene reconstruction by disentangling the static and dynamic parts within a SLAM system. The poses are tracked robustly with a novel motion masking strategy, and dynamic parts are reconstructed leveraging a progressive adaptation of a Motion Scaffolds graph. Our method yields novel view renderings competitive to offline methods and achieves on-par tracking with state-of-the-art dynamic SLAM methods. |
| title | ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2509.17864 |