TSGL：用于3DGS压缩的教师-学生图学习
TSGL: Teacher-Student Graph Learning for 3DGS Compression
浏览论文内容
中文总结 AI 辅助
本文提出TSGL方法，利用教师-学生图学习对3DGS模型进行训练后压缩，通过图傅里叶变换实现27-33倍压缩且PSNR损失小于0.6dB，优于现有方法。
中文摘要 AI 辅助
3D高斯泼溅（3DGS）是一种流行的新视角合成表示方法。然而，3DGS包含数百万个高斯图元，每个图元具有丰富的属性，导致文件体积庞大。我们提出了一种基于教师-学生图学习（TSGL）的新型3DGS压缩方法，该方法直接作用于已训练好的模型，无需重新训练3DGS或访问训练图像。具体而言，对于每个高斯图元块，我们使用解码后的位置和DC球谐（SH）系数作为预测器，通过教师-学生模型学习一个信号相关的几何图G，该图编码相邻高斯之间的成对相似性。给定G，我们对剩余属性执行图傅里叶变换（GFT），使得信号能量主要投影到低频系数上，从而实现紧凑表示。在三个标准基准上，该方法实现了27倍至33倍的压缩，PSNR损失小于0.6 dB，在文件大小和渲染质量方面均优于近期训练后压缩方法。
英文摘要
3D Gaussian Splatting (3DGS) is a popular representation for novel view synthesis. However, 3DGS contains millions of Gaussian primitives, each with rich attributes, resulting in large file sizes. We propose a novel 3DGS compression method based on Teacher-Student Graph Learning (TSGL) that operates directly on a trained model, without 3DGS retraining or access to training images. Specifically, for each block of Gaussian primitives, using decoded positions and DC spherical harmonic (SH) coefficients as predictors, we learn a signal-dependent geometry graph G encoding the pairwise similarities between neighbouring Gaussians via a teacher-student model. Given G, we perform Graph Fourier Transform (GFT) on the remaining attributes, so that signal energies are predominantly projected into the low-frequency coefficients for compact representation. On three standard benchmarks, the method reaches 27x to 33x compression with less than 0.6 dB of PSNR loss, improving on recent post-training compression methods in both size and rendering quality.
发表机构
- York University, Canada
机构由 AI 辅助整理，请以论文原文为准。
