Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2602.03538 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910010438582272 |
|---|---|
| author | Zheng, Zihan Wu, Zhenglong Wang, Xuanxuan Zhong, Houqiang Zhang, Xiaoyun Hu, Qiang Zhai, Guangtao Zhang, Wenjun |
| author_facet | Zheng, Zihan Wu, Zhenglong Wang, Xuanxuan Zhong, Houqiang Zhang, Xiaoyun Hu, Qiang Zhai, Guangtao Zhang, Wenjun |
| contents | While Dynamic Gaussian Splatting enables high-fidelity 4D reconstruction, its deployment is severely hindered by a fundamental dilemma: unconstrained densification leads to excessive memory consumption incompatible with edge devices, whereas heuristic pruning fails to achieve optimal rendering quality under preset Gaussian budgets. In this work, we propose Constrained Dynamic Gaussian Splatting (CDGS), a novel framework that formulates dynamic scene reconstruction as a budget-constrained optimization problem to enforce a strict, user-defined Gaussian budget during training. Our key insight is to introduce a differentiable budget controller as the core optimization driver. Guided by a multi-modal unified importance score, this controller fuses geometric, motion, and perceptual cues for precise capacity regulation. To maximize the utility of this fixed budget, we further decouple the optimization of static and dynamic elements, employing an adaptive allocation mechanism that dynamically distributes capacity based on motion complexity. Furthermore, we implement a three-phase training strategy to seamlessly integrate these constraints, ensuring precise adherence to the target count. Coupled with a dual-mode hybrid compression scheme, CDGS not only strictly adheres to hardware constraints (error < 2%}) but also pushes the Pareto frontier of rate-distortion performance. Extensive experiments demonstrate that CDGS delivers optimal rendering quality under varying capacity limits, achieving over 3x compression compared to state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03538 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Constrained Dynamic Gaussian Splatting Zheng, Zihan Wu, Zhenglong Wang, Xuanxuan Zhong, Houqiang Zhang, Xiaoyun Hu, Qiang Zhai, Guangtao Zhang, Wenjun Computer Vision and Pattern Recognition While Dynamic Gaussian Splatting enables high-fidelity 4D reconstruction, its deployment is severely hindered by a fundamental dilemma: unconstrained densification leads to excessive memory consumption incompatible with edge devices, whereas heuristic pruning fails to achieve optimal rendering quality under preset Gaussian budgets. In this work, we propose Constrained Dynamic Gaussian Splatting (CDGS), a novel framework that formulates dynamic scene reconstruction as a budget-constrained optimization problem to enforce a strict, user-defined Gaussian budget during training. Our key insight is to introduce a differentiable budget controller as the core optimization driver. Guided by a multi-modal unified importance score, this controller fuses geometric, motion, and perceptual cues for precise capacity regulation. To maximize the utility of this fixed budget, we further decouple the optimization of static and dynamic elements, employing an adaptive allocation mechanism that dynamically distributes capacity based on motion complexity. Furthermore, we implement a three-phase training strategy to seamlessly integrate these constraints, ensuring precise adherence to the target count. Coupled with a dual-mode hybrid compression scheme, CDGS not only strictly adheres to hardware constraints (error < 2%}) but also pushes the Pareto frontier of rate-distortion performance. Extensive experiments demonstrate that CDGS delivers optimal rendering quality under varying capacity limits, achieving over 3x compression compared to state-of-the-art methods. |
| title | Constrained Dynamic Gaussian Splatting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.03538 |