用扩散模型修复压缩后的3D高斯点云，实现超高压缩下的高质量渲染。
ExGS: Extreme 3D Gaussian Compression with Diffusion Priors
- 不重优化，直接剪枝+扩散修复，快速压缩3D高斯场景。
- 最高100倍压缩率，模型从354.77MB减至3.31MB，仍保持高画质。
- 适合资源受限环境部署，支持实时重建，适合视觉质量敏感应用。
神经场景表示如3D高斯溅射（3DGS）实现了高质量的神经渲染，但其巨大的存储与传输开销限制了在资源受限环境中的部署。现有压缩方法或依赖昂贵的优化（慢且场景特定），或采用无训练的剪枝与量化（高压缩下画质下降）。相比之下，近期数据驱动方法为突破这一权衡提供了新方向。本文提出ExGS，一种前馈式框架，融合通用高斯压缩（UGC）与GaussPainter，实现极端3DGS压缩。UGC通过免重优化剪枝大幅减少高斯原语，仅保留关键信息；GaussPainter则利用强大的扩散先验与掩码引导重构，从严重剪枝的场景中恢复高质量渲染。不同于传统修补，GaussPainter不仅能填补缺失区域，还能增强可见像素，显著提升劣化图像质量。为保证实用性，采用轻量级VAE与单步扩散设计，实现实时恢复。该框架在极端条件下仍可实现超过100倍压缩（典型354.77MB模型降至约3.31MB），同时保持保真度并显著提升画质。结果凸显了扩散先验在连接极端压缩与高质量神经渲染中的核心作用。代码将开源于：https://github.com/chenttt2001/ExGS
原文摘要 · Abstract (English)
Neural scene representations, such as 3D Gaussian Splatting (3DGS), have enabled high-quality neural rendering; however, their large storage and transmission costs hinder deployment in resource-constrained environments. Existing compression methods either rely on costly optimization, which is slow and scene-specific, or adopt training-free pruning and quantization, which degrade rendering quality under high compression ratios. In contrast, recent data-driven approaches provide a promising direction to overcome this trade-off, enabling efficient compression while preserving high rendering quality. We introduce ExGS, a novel feed-forward framework that unifies Universal Gaussian Compression (UGC) with GaussPainter for Extreme 3DGS compression. UGC performs re-optimization-free pruning to aggressively reduce Gaussian primitives while retaining only essential information, whereas GaussPainter leverages powerful diffusion priors with mask-guided refinement to restore high-quality renderings from heavily pruned Gaussian scenes. Unlike conventional inpainting, GaussPainter not only fills in missing regions but also enhances visible pixels, yielding substantial improvements in degraded renderings. To ensure practicality, it adopts a lightweight VAE and a one-step diffusion design, enabling real-time restoration. Our framework can even achieve over 100X compression (reducing a typical 354.77 MB model to about 3.31 MB) while preserving fidelity and significantly improving image quality under challenging conditions. These results highlight the central role of diffusion priors in bridging the gap between extreme compression and high-quality neural rendering. Our code repository will be released at: https://github.com/chenttt2001/ExGS
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。