OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915572111900672 |
|---|---|
| author | Huang, Mark He Foo, Lin Geng Theobalt, Christian Sun, Ying Soh, De Wen |
| author_facet | Huang, Mark He Foo, Lin Geng Theobalt, Christian Sun, Ying Soh, De Wen |
| contents | Free-moving object reconstruction from monocular video remains challenging, particularly without reliable pose or depth cues and under arbitrary object motion. We introduce OnlineSplatter, a novel online feed-forward framework generating high-quality, object-centric 3D Gaussians directly from RGB frames without requiring camera pose, depth priors, or bundle optimization. Our approach anchors reconstruction using the first frame and progressively refines the object representation through a dense Gaussian primitive field, maintaining constant computational cost regardless of video sequence length. Our core contribution is a dual-key memory module combining latent appearance-geometry keys with explicit directional keys, robustly fusing current frame features with temporally aggregated object states. This design enables effective handling of free-moving objects via spatial-guided memory readout and an efficient sparsification mechanism, ensuring comprehensive yet compact object coverage. Evaluations on real-world datasets demonstrate that OnlineSplatter significantly outperforms state-of-the-art pose-free reconstruction baselines, consistently improving with more observations while maintaining constant memory and runtime. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20605 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects Huang, Mark He Foo, Lin Geng Theobalt, Christian Sun, Ying Soh, De Wen Computer Vision and Pattern Recognition Artificial Intelligence I.4.5; I.2.6 Free-moving object reconstruction from monocular video remains challenging, particularly without reliable pose or depth cues and under arbitrary object motion. We introduce OnlineSplatter, a novel online feed-forward framework generating high-quality, object-centric 3D Gaussians directly from RGB frames without requiring camera pose, depth priors, or bundle optimization. Our approach anchors reconstruction using the first frame and progressively refines the object representation through a dense Gaussian primitive field, maintaining constant computational cost regardless of video sequence length. Our core contribution is a dual-key memory module combining latent appearance-geometry keys with explicit directional keys, robustly fusing current frame features with temporally aggregated object states. This design enables effective handling of free-moving objects via spatial-guided memory readout and an efficient sparsification mechanism, ensuring comprehensive yet compact object coverage. Evaluations on real-world datasets demonstrate that OnlineSplatter significantly outperforms state-of-the-art pose-free reconstruction baselines, consistently improving with more observations while maintaining constant memory and runtime. |
| title | OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence I.4.5; I.2.6 |
| url | https://arxiv.org/abs/2510.20605 |