TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints
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_ | 1866911278496219136 |
|---|---|
| author | Shi, Dongbo Cao, Shen Fan, Lubin Wu, Bojian Guo, Jinhui Liu, Ligang Chen, Renjie |
| author_facet | Shi, Dongbo Cao, Shen Fan, Lubin Wu, Bojian Guo, Jinhui Liu, Ligang Chen, Renjie |
| contents | We present TrackGS, a novel method to integrate global feature tracks with 3D Gaussian Splatting (3DGS) for COLMAP-free novel view synthesis. While 3DGS delivers impressive rendering quality, its reliance on accurate precomputed camera parameters remains a significant limitation. Existing COLMAP-free approaches depend on local constraints that fail in complex scenarios. Our key innovation lies in leveraging feature tracks to establish global geometric constraints, enabling simultaneous optimization of camera parameters and 3D Gaussians. Specifically, we: (1) introduce track-constrained Gaussians that serve as geometric anchors, (2) propose novel 2D and 3D track losses to enforce multi-view consistency, and (3) derive differentiable formulations for camera intrinsics optimization. Extensive experiments on challenging real-world and synthetic datasets demonstrate state-of-the-art performance, with much lower pose error than previous methods while maintaining superior rendering quality. Our approach eliminates the need for COLMAP preprocessing, making 3DGS more accessible for practical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_19800 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints Shi, Dongbo Cao, Shen Fan, Lubin Wu, Bojian Guo, Jinhui Liu, Ligang Chen, Renjie Computer Vision and Pattern Recognition We present TrackGS, a novel method to integrate global feature tracks with 3D Gaussian Splatting (3DGS) for COLMAP-free novel view synthesis. While 3DGS delivers impressive rendering quality, its reliance on accurate precomputed camera parameters remains a significant limitation. Existing COLMAP-free approaches depend on local constraints that fail in complex scenarios. Our key innovation lies in leveraging feature tracks to establish global geometric constraints, enabling simultaneous optimization of camera parameters and 3D Gaussians. Specifically, we: (1) introduce track-constrained Gaussians that serve as geometric anchors, (2) propose novel 2D and 3D track losses to enforce multi-view consistency, and (3) derive differentiable formulations for camera intrinsics optimization. Extensive experiments on challenging real-world and synthetic datasets demonstrate state-of-the-art performance, with much lower pose error than previous methods while maintaining superior rendering quality. Our approach eliminates the need for COLMAP preprocessing, making 3DGS more accessible for practical applications. |
| title | TrackGS: Optimizing COLMAP-Free 3D Gaussian Splatting with Global Track Constraints |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.19800 |