StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909549077725184 |
|---|---|
| author | LI, Yang Wang, Jinglu Chu, Lei Li, Xiao Kao, Shiu-hong Chen, Ying-Cong Lu, Yan |
| author_facet | LI, Yang Wang, Jinglu Chu, Lei Li, Xiao Kao, Shiu-hong Chen, Ying-Cong Lu, Yan |
| contents | The advent of 3D Gaussian Splatting (3DGS) has advanced 3D scene reconstruction and novel view synthesis. With the growing interest of interactive applications that need immediate feedback, online 3DGS reconstruction in real-time is in high demand. However, none of existing methods yet meet the demand due to three main challenges: the absence of predetermined camera parameters, the need for generalizable 3DGS optimization, and the necessity of reducing redundancy. We propose StreamGS, an online generalizable 3DGS reconstruction method for unposed image streams, which progressively transform image streams to 3D Gaussian streams by predicting and aggregating per-frame Gaussians. Our method overcomes the limitation of the initial point reconstruction \cite{dust3r} in tackling out-of-domain (OOD) issues by introducing a content adaptive refinement. The refinement enhances cross-frame consistency by establishing reliable pixel correspondences between adjacent frames. Such correspondences further aid in merging redundant Gaussians through cross-frame feature aggregation. The density of Gaussians is thereby reduced, empowering online reconstruction by significantly lowering computational and memory costs. Extensive experiments on diverse datasets have demonstrated that StreamGS achieves quality on par with optimization-based approaches but does so 150 times faster, and exhibits superior generalizability in handling OOD scenes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_06235 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams LI, Yang Wang, Jinglu Chu, Lei Li, Xiao Kao, Shiu-hong Chen, Ying-Cong Lu, Yan Computer Vision and Pattern Recognition The advent of 3D Gaussian Splatting (3DGS) has advanced 3D scene reconstruction and novel view synthesis. With the growing interest of interactive applications that need immediate feedback, online 3DGS reconstruction in real-time is in high demand. However, none of existing methods yet meet the demand due to three main challenges: the absence of predetermined camera parameters, the need for generalizable 3DGS optimization, and the necessity of reducing redundancy. We propose StreamGS, an online generalizable 3DGS reconstruction method for unposed image streams, which progressively transform image streams to 3D Gaussian streams by predicting and aggregating per-frame Gaussians. Our method overcomes the limitation of the initial point reconstruction \cite{dust3r} in tackling out-of-domain (OOD) issues by introducing a content adaptive refinement. The refinement enhances cross-frame consistency by establishing reliable pixel correspondences between adjacent frames. Such correspondences further aid in merging redundant Gaussians through cross-frame feature aggregation. The density of Gaussians is thereby reduced, empowering online reconstruction by significantly lowering computational and memory costs. Extensive experiments on diverse datasets have demonstrated that StreamGS achieves quality on par with optimization-based approaches but does so 150 times faster, and exhibits superior generalizability in handling OOD scenes. |
| title | StreamGS: Online Generalizable Gaussian Splatting Reconstruction for Unposed Image Streams |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.06235 |