GFix: Perceptually Enhanced Gaussian Splatting Video Compression
This work addresses video compression for applications requiring high perceptual quality, representing an incremental improvement over existing 3DGS-based methods.
The paper tackles the problem of visual artifacts and low compression ratios in 3D Gaussian Splatting-based video codecs by proposing GFix, a content-adaptive framework with a single-step diffusion model and modulated LoRA scheme, resulting in up to 72.1% BD-rate savings in LPIPS and 21.4% in FID compared to GSVC.
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.