arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新，休息一下吧，周末愉快~~
arXiv 2401.02436cs.CVcs.GR

用于加速新视角合成的压缩3D Gaussian Splatting

Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis

Technical University of Munich（慕尼黑工业大学）

Simon Niedermayr, Josef Stumpfegger, Rüdiger Westermann

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出压缩3D Gaussian splat表示，结合敏感度感知向量聚类和量化感知训练，在保持视觉质量的同时实现31倍压缩与最高4倍渲染加速。

摘要：

近来，基于优化的3D Gaussian splat表示的高保真场景重建已被提出，用于从稀疏图像集进行新视角合成。要使此类表示适用于网络流式传输和低功耗设备渲染等应用，需要显著降低内存消耗并提高渲染效率。我们提出一种压缩的3D Gaussian splat表示，利用敏感度感知向量聚类与量化感知训练来压缩方向颜色和Gaussian参数。学习得到的码本具有低比特率，并在真实场景上实现高达31倍的压缩率，同时视觉质量仅有极小下降。我们证明，压缩后的splat表示可在轻量级GPU上通过硬件光栅化高效渲染，帧率比已报道的优化GPU计算管线最高高出4倍。跨多个数据集的大量实验证明了所提方法的鲁棒性和渲染速度。

英文摘要：

Recently, high-fidelity scene reconstruction with an optimized 3D Gaussian splat representation has been introduced for novel view synthesis from sparse image sets. Making such representations suitable for applications like network streaming and rendering on low-power devices requires significantly reduced memory consumption as well as improved rendering efficiency. We propose a compressed 3D Gaussian splat representation that utilizes sensitivity-aware vector clustering with quantization-aware training to compress directional colors and Gaussian parameters. The learned codebooks have low bitrates and achieve a compression rate of up to $31\times$ on real-world scenes with only minimal degradation of visual quality. We demonstrate that the compressed splat representation can be efficiently rendered with hardware rasterization on lightweight GPUs at up to $4\times$ higher framerates than reported via an optimized GPU compute pipeline. Extensive experiments across multiple datasets demonstrate the robustness and rendering speed of the proposed approach.

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。

↑