Motion Matters: Compact Gaussian Streaming for Free-Viewpoint Video Reconstruction

TL;DR

This paper introduces Compact Gaussian Streaming, a novel method for free-viewpoint video reconstruction that significantly reduces storage needs by modeling motion with keypoints, enabling efficient and high-quality dynamic scene rendering.

Contribution

It proposes a keypoint-driven motion representation framework that reduces storage by over 159 times compared to existing methods, improving efficiency without sacrificing quality.

Findings

Achieves over 159x storage reduction compared to 3DGStream.

Outperforms state-of-the-art QUEEN method with 14x less storage.

Maintains competitive visual fidelity and rendering speed.

Abstract

3D Gaussian Splatting (3DGS) has emerged as a high-fidelity and efficient paradigm for online free-viewpoint video (FVV) reconstruction, offering viewers rapid responsiveness and immersive experiences. However, existing online methods face challenge in prohibitive storage requirements primarily due to point-wise modeling that fails to exploit the motion properties. To address this limitation, we propose a novel Compact Gaussian Streaming (ComGS) framework, leveraging the locality and consistency of motion in dynamic scene, that models object-consistent Gaussian point motion through keypoint-driven motion representation. By transmitting only the keypoint attributes, this framework provides a more storage-efficient solution. Specifically, we first identify a sparse set of motion-sensitive keypoints localized within motion regions using a viewspace gradient difference strategy. Equipped with these keypoints, we propose an adaptive motion-driven mechanism that predicts a spatial influence field for propagating keypoint motion to neighboring Gaussian points with similar motion. Moreover, ComGS adopts an error-aware correction strategy for key frame reconstruction that selectively refines erroneous regions and mitigates error accumulation without unnecessary overhead. Overall, ComGS achieves a remarkable storage reduction of over 159 X compared to 3DGStream and 14 X compared to the SOTA method QUEEN, while maintaining competitive visual fidelity and rendering speed.