SizeGS: Size-aware Compression of 3D Gaussian Splatting via Mixed Integer Programming

TL;DR

This paper introduces SizeGS, a size-aware compression method for 3D Gaussian Splatting that optimizes hyperparameters via mixed-integer programming to efficiently reduce data size while maintaining high visual quality.

Contribution

It formulates size-aware compression as a mixed-integer nonlinear programming problem and proposes a decoupled solution with estimators and CUDA implementation for efficient hyperparameter search.

Findings

Achieves state-of-the-art post-training compression performance.

Maintains comparable quality to training-based methods after fine-tuning.

Efficient hyperparameter search reduces compression time significantly.

Abstract

Recent advances in 3D Gaussian Splatting (3DGS) have greatly improved 3D reconstruction. However, its substantial data size poses a significant challenge for transmission and storage. While many compression techniques have been proposed, they fail to efficiently adapt to fluctuating network bandwidth, leading to resource wastage. We address this issue from the perspective of size-aware compression, where we aim to compress 3DGS to a desired size by quickly searching for suitable hyperparameters. Through a measurement study, we identify key hyperparameters that affect the size -- namely, the reserve ratio of Gaussians and bit-width settings for Gaussian attributes. Then, we formulate this hyperparameter optimization problem as a mixed-integer nonlinear programming (MINLP) problem, with the goal of maximizing visual quality while respecting the size budget constraint. To solve the MINLP, we decouple this problem into two parts: discretely sampling the reserve ratio and determining the bit-width settings using integer linear programming (ILP). To solve the ILP more quickly and accurately, we design a quality loss estimator and a calibrated size estimator, as well as implement a CUDA kernel. Extensive experiments on multiple 3DGS variants demonstrate that our method achieves state-of-the-art performance in post-training compression. Furthermore, our method can achieve comparable quality to leading training-required methods after fine-tuning.