ADC-GS: Anchor-Driven Deformable and Compressed Gaussian Splatting for Dynamic Scene Reconstruction
This addresses the computational and storage bottlenecks in dynamic scene reconstruction for applications like VR/AR and computer vision, though it appears incremental as it builds on existing 4D Gaussian Splatting methods.
The paper tackles the problem of inefficient dynamic scene reconstruction in 4D Gaussian Splatting by proposing ADC-GS, which organizes Gaussian primitives into an anchor-based structure with hierarchical motion capture and rate-distortion optimization. The result is a 300%-800% faster rendering speed and state-of-the-art storage efficiency while maintaining rendering quality.
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.