GFix: Perceptually Enhanced Gaussian Splatting Video Compression

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Teng, Siyue, Gao, Ge, Danier, Duolikun, Jiang, Yuxuan, Zhang, Fan, Davis, Thomas, Liu, Zoe, Bull, David
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911257840320512
author Teng, Siyue
Gao, Ge
Danier, Duolikun
Jiang, Yuxuan
Zhang, Fan
Davis, Thomas
Liu, Zoe
Bull, David
author_facet Teng, Siyue
Gao, Ge
Danier, Duolikun
Jiang, Yuxuan
Zhang, Fan
Davis, Thomas
Liu, Zoe
Bull, David
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06953
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GFix: Perceptually Enhanced Gaussian Splatting Video Compression
Teng, Siyue
Gao, Ge
Danier, Duolikun
Jiang, Yuxuan
Zhang, Fan
Davis, Thomas
Liu, Zoe
Bull, David
Computer Vision and Pattern Recognition
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.
title GFix: Perceptually Enhanced Gaussian Splatting Video Compression
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.06953