P-4DGS：具有90倍压缩率的预测性4D高斯泼溅
P-4DGS: Predictive 4D Gaussian Splatting with 90$\times$ Compression
AI总结：
针对动态3D高斯泼溅的时空冗余导致内存过高问题，提出P-4DGS，通过基于3D锚点的时空预测模块与自适应量化及熵编码实现紧凑4D建模，在保持最先进重建质量与最快渲染速度的同时，在真实场景上实现高达90倍的压缩。
摘要：
3D高斯泼溅（3DGS）因其卓越的场景表示保真度和实时渲染性能，特别是在动态3D场景重建（即4D重建）中，而引起了广泛关注。然而，尽管取得了令人鼓舞的结果，大多数现有算法忽略了动态场景中固有的巨大时空冗余，导致内存消耗过高。为了解决这个问题，我们提出了P-4DGS，一种用于紧凑4D场景建模的新型动态3DGS表示。受视频压缩中常用的帧内和帧间预测技术的启发，我们首先设计了一个基于3D锚点的时空预测模块，以充分利用不同3D高斯基元之间的时空相关性。随后，我们采用自适应量化策略结合基于上下文的熵编码，进一步减小3D锚点的尺寸，从而实现更高的压缩效率。为了评估我们提出的P-4DGS与其他动态3DGS表示相比的率失真性能，我们在合成和真实世界数据集上进行了大量实验。实验结果表明，我们的方法实现了最先进的重建质量和最快的渲染速度，且存储占用极低（平均约1MB），在合成和真实场景上分别实现了高达40倍和90倍的压缩。
英文摘要：
3D Gaussian Splatting (3DGS) has garnered significant attention due to its superior scene representation fidelity and real-time rendering performance, especially for dynamic 3D scene reconstruction (\textit{i.e.}, 4D reconstruction). However, despite achieving promising results, most existing algorithms overlook the substantial temporal and spatial redundancies inherent in dynamic scenes, leading to prohibitive memory consumption. To address this, we propose P-4DGS, a novel dynamic 3DGS representation for compact 4D scene modeling. Inspired by intra- and inter-frame prediction techniques commonly used in video compression, we first design a 3D anchor point-based spatial-temporal prediction module to fully exploit the spatial-temporal correlations across different 3D Gaussian primitives. Subsequently, we employ an adaptive quantization strategy combined with context-based entropy coding to further reduce the size of the 3D anchor points, thereby achieving enhanced compression efficiency. To evaluate the rate-distortion performance of our proposed P-4DGS in comparison with other dynamic 3DGS representations, we conduct extensive experiments on both synthetic and real-world datasets. Experimental results demonstrate that our approach achieves state-of-the-art reconstruction quality and the fastest rendering speed, with a remarkably low storage footprint (around \textbf{1MB} on average), achieving up to \textbf{40$\times$} and \textbf{90$\times$} compression on synthetic and real-world scenes, respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
