Nix and Fix: Targeting 1000x Compression of 3D Gaussian Splatting with Diffusion Models
This addresses the storage bottleneck for applications like immersive communication by enabling efficient compression of 3DGS representations.
The paper tackles the problem of high storage requirements in 3D Gaussian Splatting (3DGS) for novel view rendering by introducing NiFi, a method for extreme compression that achieves state-of-the-art perceptual quality at rates as low as 0.1 MB, with up to 1000x rate improvement over 3DGS at comparable quality.
3D Gaussian Splatting (3DGS) revolutionized novel view rendering. Instead of inferring from dense spatial points, as implicit representations do, 3DGS uses sparse Gaussians. This enables real-time performance but increases space requirements, hindering applications such as immersive communication. 3DGS compression emerged as a field aimed at alleviating this issue. While impressive progress has been made, at low rates, compression introduces artifacts that degrade visual quality significantly. We introduce NiFi, a method for extreme 3DGS compression through restoration via artifact-aware, diffusion-based one-step distillation. We show that our method achieves state-of-the-art perceptual quality at extremely low rates, down to 0.1 MB, and towards 1000x rate improvement over 3DGS at comparable perceptual performance. The code will be open-sourced upon acceptance.