PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914552601378816 |
|---|---|
| author | Deng, Yinan Dou, Jianyu Wang, Jiahui Zhao, Jingyu Yang, Yi Yue, Yufeng |
| author_facet | Deng, Yinan Dou, Jianyu Wang, Jiahui Zhao, Jingyu Yang, Yi Yue, Yufeng |
| contents | Dynamic scene reconstruction represents a fundamental yet demanding challenge in computer vision and robotics. While recent progress in 3DGS-based methods has advanced dynamic scene modeling, obtaining high-fidelity rendering and accurate tracking in scenarios with substantial, intricate motions remains significantly challenging. To address these challenges, we propose PaMoSplat, a novel dynamic Gaussian splatting framework incorporating part awareness and motion priors. Our approach is grounded in two key observations: 1) Parts serve as primitives for scene deformation, and 2) Motion cues from optical flow can effectively guide part motion. Specifically, PaMoSplat initializes by lifting multi-view segmentation masks into 3D space via graph clustering, establishing coherent Gaussian parts. For subsequent timestamps, we leverage a differential evolutionary algorithm to estimate the rigid motion of these parts using multi-view optical flow cues, providing a robust warm-start for further optimization. Additionally, PaMoSplat introduces an adaptive iteration count mechanism, internal learnable rigidity, and flow-supervised rendering loss to accelerate and optimize the training process. Comprehensive evaluations across diverse scenes, including real-world environments, demonstrate that PaMoSplat delivers superior rendering quality, improved tracking precision, and faster convergence compared to existing methods. Furthermore, it enables multiple part-level downstream applications, such as 4D scene editing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_10307 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction Deng, Yinan Dou, Jianyu Wang, Jiahui Zhao, Jingyu Yang, Yi Yue, Yufeng Computer Vision and Pattern Recognition Graphics Robotics Dynamic scene reconstruction represents a fundamental yet demanding challenge in computer vision and robotics. While recent progress in 3DGS-based methods has advanced dynamic scene modeling, obtaining high-fidelity rendering and accurate tracking in scenarios with substantial, intricate motions remains significantly challenging. To address these challenges, we propose PaMoSplat, a novel dynamic Gaussian splatting framework incorporating part awareness and motion priors. Our approach is grounded in two key observations: 1) Parts serve as primitives for scene deformation, and 2) Motion cues from optical flow can effectively guide part motion. Specifically, PaMoSplat initializes by lifting multi-view segmentation masks into 3D space via graph clustering, establishing coherent Gaussian parts. For subsequent timestamps, we leverage a differential evolutionary algorithm to estimate the rigid motion of these parts using multi-view optical flow cues, providing a robust warm-start for further optimization. Additionally, PaMoSplat introduces an adaptive iteration count mechanism, internal learnable rigidity, and flow-supervised rendering loss to accelerate and optimize the training process. Comprehensive evaluations across diverse scenes, including real-world environments, demonstrate that PaMoSplat delivers superior rendering quality, improved tracking precision, and faster convergence compared to existing methods. Furthermore, it enables multiple part-level downstream applications, such as 4D scene editing. |
| title | PaMoSplat: Part-Aware Motion-Guided Gaussian Splatting for Dynamic Scene Reconstruction |
| topic | Computer Vision and Pattern Recognition Graphics Robotics |
| url | https://arxiv.org/abs/2605.10307 |