SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912474305921024 |
|---|---|
| author | Yao, Wei Xie, Shuzhao Li, Letian Zhang, Weixiang Lai, Zhixin Dai, Shiqi Zhang, Ke Wang, Zhi |
| author_facet | Yao, Wei Xie, Shuzhao Li, Letian Zhang, Weixiang Lai, Zhixin Dai, Shiqi Zhang, Ke Wang, Zhi |
| contents | Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and the ability to characterize complex physical motions significantly limits the practical application of these methods. To tackle these problems, we propose SD-GS, a compact and efficient dynamic Gaussian splatting framework for complex dynamic scene reconstruction, featuring two key contributions. First, we introduce a deformable anchor grid, a hierarchical and memory-efficient scene representation where each anchor point derives multiple 3D Gaussians in its local spatiotemporal region and serves as the geometric backbone of the 3D scene. Second, to enhance modeling capability for complex motions, we present a deformation-aware densification strategy that adaptively grows anchors in under-reconstructed high-dynamic regions while reducing redundancy in static areas, achieving superior visual quality with fewer anchors. Experimental results demonstrate that, compared to state-of-the-art methods, SD-GS achieves an average of 60\% reduction in model size and an average of 100\% improvement in FPS, significantly enhancing computational efficiency while maintaining or even surpassing visual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_07465 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction Yao, Wei Xie, Shuzhao Li, Letian Zhang, Weixiang Lai, Zhixin Dai, Shiqi Zhang, Ke Wang, Zhi Graphics Computer Vision and Pattern Recognition Current 4D Gaussian frameworks for dynamic scene reconstruction deliver impressive visual fidelity and rendering speed, however, the inherent trade-off between storage costs and the ability to characterize complex physical motions significantly limits the practical application of these methods. To tackle these problems, we propose SD-GS, a compact and efficient dynamic Gaussian splatting framework for complex dynamic scene reconstruction, featuring two key contributions. First, we introduce a deformable anchor grid, a hierarchical and memory-efficient scene representation where each anchor point derives multiple 3D Gaussians in its local spatiotemporal region and serves as the geometric backbone of the 3D scene. Second, to enhance modeling capability for complex motions, we present a deformation-aware densification strategy that adaptively grows anchors in under-reconstructed high-dynamic regions while reducing redundancy in static areas, achieving superior visual quality with fewer anchors. Experimental results demonstrate that, compared to state-of-the-art methods, SD-GS achieves an average of 60\% reduction in model size and an average of 100\% improvement in FPS, significantly enhancing computational efficiency while maintaining or even surpassing visual quality. |
| title | SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.07465 |