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

TL;DR

ADC-GS introduces an anchor-based, hierarchical, and rate-distortion optimized Gaussian splatting method that significantly improves dynamic scene reconstruction efficiency and storage without sacrificing quality.

Contribution

It proposes a novel anchor-driven, hierarchical, and compressed Gaussian splatting framework with rate-distortion optimization for better dynamic scene reconstruction.

Findings

Achieves 300%-800% faster rendering speed.

Outperforms existing methods in storage efficiency.

Maintains high rendering quality.

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 results 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.