TC-GS：基于三平面的三维高斯泼溅压缩
TC-GS: Tri-plane based compression for 3D Gaussian Splatting
AI总结：
针对3DGS数据量大且结构无序难以压缩的问题，提出基于三平面编码高斯属性并利用KNN解码，结合位置先验与自适应小波损失，实现高效压缩且效果优于现有方法。
摘要：
近年来，三维高斯泼溅（3DGS）已成为新视角合成的重要框架，提供高保真度和快速渲染速度。然而，3DGS及其属性的大量数据阻碍了其实际应用，需要压缩技术来降低内存成本。尽管如此，3DGS的无组织形状导致压缩困难。为了将非结构化属性规范化为标准分布，我们提出了一种结构良好的三平面来编码高斯属性，利用属性分布进行压缩。为了利用相邻高斯之间的相关性，在从三平面解码高斯分布时使用K近邻（KNN）。我们还引入高斯位置信息作为位置敏感解码器的先验。此外，我们加入了自适应小波损失，旨在随着迭代次数的增加关注高频细节。我们的方法在多个数据集上的广泛实验中取得了与最先进的3D高斯泼溅压缩工作相当或更优的结果。代码发布在https://github.com/timwang2001/TC-GS。
英文摘要：
Recently, 3D Gaussian Splatting (3DGS) has emerged as a prominent framework for novel view synthesis, providing high fidelity and rapid rendering speed. However, the substantial data volume of 3DGS and its attributes impede its practical utility, requiring compression techniques for reducing memory cost. Nevertheless, the unorganized shape of 3DGS leads to difficulties in compression. To formulate unstructured attributes into normative distribution, we propose a well-structured tri-plane to encode Gaussian attributes, leveraging the distribution of attributes for compression. To exploit the correlations among adjacent Gaussians, K-Nearest Neighbors (KNN) is used when decoding Gaussian distribution from the Tri-plane. We also introduce Gaussian position information as a prior of the position-sensitive decoder. Additionally, we incorporate an adaptive wavelet loss, aiming to focus on the high-frequency details as iterations increase. Our approach has achieved results that are comparable to or surpass that of SOTA 3D Gaussians Splatting compression work in extensive experiments across multiple datasets. The codes are released at https://github.com/timwang2001/TC-GS.
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。
