用三平面结构压缩3D高斯点云，提升存储效率
TC-GS: Tri-plane based compression for 3D Gaussian Splatting
- 设计三平面结构编码高斯属性，使无序数据有序化
- 通过KNN和自适应小波损失，保留高频细节，压缩后质量接近顶尖水平
- 适合需要高效存储的3D内容应用，如移动端渲染
近期，3D高斯点云（3DGS）已成为新颖视图合成的主流框架，具备高保真度与快速渲染速度。然而，3DGS庞大的数据量及其无组织特性限制了其实际应用，需压缩技术降低内存开销。由于3DGS结构无序，压缩面临挑战。为此，我们提出一种结构化的三平面表示，将高斯属性映射为规范分布，实现有效压缩。解码时引入邻近高斯的K-最近邻（KNN）关系，并以高斯位置作为位置敏感解码器的先验信息。此外，采用自适应小波损失，在迭代过程中更关注高频细节。在多个数据集上的大量实验表明，该方法在压缩性能上达到或超越当前最优3DGS压缩方案。代码已公开于https://github.com/timwang2001/TC-GS。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。