用扩散模型修复3D高斯点云视频压缩中的伪影，提升画质并节省带宽。
GFix: Perceptually Enhanced Gaussian Splatting Video Compression
- 设计轻量级单步扩散模型，自适应增强3D高斯点云视频的视觉质量。
- 在LPIPS上比GSVC降低72.1%码率，FID指标提升21.4%。
- 采用可压缩的调制LoRA结构，实现高效模型更新，适合部署于边缘设备。
3D高斯点云（3DGS）通过显式表示与快速渲染提升了3D场景重建能力，展现出在视频压缩等低层视觉任务中的潜力。然而，现有基于3DGS的视频编解码器普遍存在明显视觉伪影且压缩比偏低。本文针对3DGS视频压缩的感知质量提升问题，假设其渲染与量化伪影类似于扩散模型训练中采样的噪声潜空间。基于此，提出内容自适应框架GFix，包含一个轻量级、单步扩散模型作为即插即用的神经增强器。此外，为提升压缩效率，设计一种调制型LoRA方案：冻结低秩分解参数，仅调制中间隐藏状态，实现对扩散主干的高效适配与高度可压缩更新。实验表明，GFix在感知质量上显著优于GSVC，LPIPS指标下最高实现72.1%的BD-rate节省，FID指标提升21.4%。
原文摘要 · Abstract (English)
3D Gaussian Splatting (3DGS) enhances 3D scene reconstruction through explicit representation and fast rendering, demonstrating potential benefits for various low-level vision tasks, including video compression. However, existing 3DGS-based video codecs generally exhibit more noticeable visual artifacts and relatively low compression ratios. In this paper, we specifically target the perceptual enhancement of 3DGS-based video compression, based on the assumption that artifacts from 3DGS rendering and quantization resemble noisy latents sampled during diffusion training. Building on this premise, we propose a content-adaptive framework, GFix, comprising a streamlined, single-step diffusion model that serves as an off-the-shelf neural enhancer. Moreover, to increase compression efficiency, We propose a modulated LoRA scheme that freezes the low-rank decompositions and modulates the intermediate hidden states, thereby achieving efficient adaptation of the diffusion backbone with highly compressible updates. Experimental results show that GFix delivers strong perceptual quality enhancement, outperforming GSVC with up to 72.1% BD-rate savings in LPIPS and 21.4% in FID.
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。