---
title: "ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction"
authors:
  - "He Huang"
  - "Qi Yang"
  - "Mufan Liu"
  - "Yiling Xu"
  - "Zhu Li"
doi: "10.24963/ijcai.2025/132"
url: "https://ijcai.org/proceedings/2025/132"
pdf: "https://ijcai.org/proceedings/2025/0132.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "1179-1187"
track: "Main Track"
keywords:
  - "Computer Vision: CV: Efficiency and Optimization"
  - "Computer Vision: CV: Image and video synthesis and generation"
---

# ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction

He Huang, Qi Yang, Mufan Liu, Yiling Xu, Zhu Li

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 1179-1187. DOI: [10.24963/ijcai.2025/132](https://doi.org/10.24963/ijcai.2025/132)

## Abstract

Existing 4D Gaussian Splatting methods rely on per-Gaussian deformation from a canonical space to target frames, which overlooks redundancy among adjacent Gaussian primitives and result in suboptimal performance. To address this limitation, we propose Anchor-Driven Deformable and Compressed Gaussian Splatting (ADC-GS), a compact and efficient representation for dynamic scene reconstruction. Specifically, ADC-GS organizes Gaussian primitives into an anchor-based structure within the canonical space, enhanced by a temporal significance-based anchor refinement strategy. To reduce deformation redundancy, ADC-GS introduces a hierarchical coarse-to-fine pipeline that captures motions at varying granularities. Moreover, a rate-distortion optimization is adopted to achieve an optimal balance between bitrate consumption and representation fidelity. Experimental results demonstrate that ADC-GS outperforms the per-Gaussian deformation approaches in rendering speed by 300%-800% while achieving state-of-the-art storage efficiency without compromising rendering quality. The code is released at https://github.com/H-Huang774/ADC-GS.git.