Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.02660 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915708326117376 |
|---|---|
| author | Xu, Yijun Zhang, Jingrui Chen, Yuhan Wang, Dingwen Yu, Lei He, Chu |
| author_facet | Xu, Yijun Zhang, Jingrui Chen, Yuhan Wang, Dingwen Yu, Lei He, Chu |
| contents | Modeling complex rigid motion across large spatiotemporal spans remains an unresolved challenge in dynamic reconstruction. Existing paradigms are mainly confined to short-term, small-scale deformation and offer limited consideration for physical consistency. This study proposes PMGS, focusing on reconstructing Projectile Motion via 3D Gaussian Splatting. The workflow comprises two stages: 1) Target Modeling: achieving object-centralized reconstruction through dynamic scene decomposition and an improved point density control; 2) Motion Recovery: restoring full motion sequences by learning per-frame SE(3) poses. We introduce an acceleration consistency constraint to bridge Newtonian mechanics and pose estimation, and design a dynamic simulated annealing strategy that adaptively schedules learning rates based on motion states. Furthermore, we devise a Kalman fusion scheme to optimize error accumulation from multi-source observations to mitigate disturbances. Experiments show PMGS's superior performance in reconstructing high-speed nonlinear rigid motion compared to mainstream dynamic methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02660 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian Splatting Xu, Yijun Zhang, Jingrui Chen, Yuhan Wang, Dingwen Yu, Lei He, Chu Computer Vision and Pattern Recognition Modeling complex rigid motion across large spatiotemporal spans remains an unresolved challenge in dynamic reconstruction. Existing paradigms are mainly confined to short-term, small-scale deformation and offer limited consideration for physical consistency. This study proposes PMGS, focusing on reconstructing Projectile Motion via 3D Gaussian Splatting. The workflow comprises two stages: 1) Target Modeling: achieving object-centralized reconstruction through dynamic scene decomposition and an improved point density control; 2) Motion Recovery: restoring full motion sequences by learning per-frame SE(3) poses. We introduce an acceleration consistency constraint to bridge Newtonian mechanics and pose estimation, and design a dynamic simulated annealing strategy that adaptively schedules learning rates based on motion states. Furthermore, we devise a Kalman fusion scheme to optimize error accumulation from multi-source observations to mitigate disturbances. Experiments show PMGS's superior performance in reconstructing high-speed nonlinear rigid motion compared to mainstream dynamic methods. |
| title | PMGS: Reconstruction of Projectile Motion Across Large Spatiotemporal Spans via 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2508.02660 |