Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2601.05584 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918279139819520 |
|---|---|
| author | Lu, Nengbo Pan, Minghua Sun, Shaohua Liang, Yizhou |
| author_facet | Lu, Nengbo Pan, Minghua Sun, Shaohua Liang, Yizhou |
| contents | In the field of 3D dynamic scene reconstruction, how to balance model convergence rate and rendering quality has long been a critical challenge that urgently needs to be addressed, particularly in high-precision modeling of scenes with complex dynamic motions. To tackle this issue, this study proposes the GS-DMSR method. By quantitatively analyzing the dynamic evolution process of Gaussian attributes, this mechanism achieves adaptive gradient focusing, enabling it to dynamically identify significant differences in the motion states of Gaussian models. It then applies differentiated optimization strategies to Gaussian models with varying degrees of significance, thereby significantly improving the model convergence rate. Additionally, this research integrates a multi-scale manifold enhancement module, which leverages the collaborative optimization of an implicit nonlinear decoder and an explicit deformation field to enhance the modeling efficiency for complex deformation scenes. Experimental results demonstrate that this method achieves a frame rate of up to 96 FPS on synthetic datasets, while effectively reducing both storage overhead and training time.Our code and data are available at https://anonymous.4open.science/r/GS-DMSR-2212. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05584 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GS-DMSR: Dynamic Sensitive Multi-scale Manifold Enhancement for Accelerated High-Quality 3D Gaussian Splatting Lu, Nengbo Pan, Minghua Sun, Shaohua Liang, Yizhou Computer Vision and Pattern Recognition Artificial Intelligence In the field of 3D dynamic scene reconstruction, how to balance model convergence rate and rendering quality has long been a critical challenge that urgently needs to be addressed, particularly in high-precision modeling of scenes with complex dynamic motions. To tackle this issue, this study proposes the GS-DMSR method. By quantitatively analyzing the dynamic evolution process of Gaussian attributes, this mechanism achieves adaptive gradient focusing, enabling it to dynamically identify significant differences in the motion states of Gaussian models. It then applies differentiated optimization strategies to Gaussian models with varying degrees of significance, thereby significantly improving the model convergence rate. Additionally, this research integrates a multi-scale manifold enhancement module, which leverages the collaborative optimization of an implicit nonlinear decoder and an explicit deformation field to enhance the modeling efficiency for complex deformation scenes. Experimental results demonstrate that this method achieves a frame rate of up to 96 FPS on synthetic datasets, while effectively reducing both storage overhead and training time.Our code and data are available at https://anonymous.4open.science/r/GS-DMSR-2212. |
| title | GS-DMSR: Dynamic Sensitive Multi-scale Manifold Enhancement for Accelerated High-Quality 3D Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2601.05584 |