TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering

TL;DR

TraGraph-GS introduces a graph-based spatial partitioning and progressive rendering approach to improve large-scale scene view synthesis, addressing limitations of existing Gaussian splatting methods.

Contribution

It proposes a novel trajectory graph-based partitioning and rendering strategy that enhances accuracy and texture preservation in large-scale scene synthesis.

Findings

Achieves 1.86 dB higher PSNR on aerial datasets

Achieves 1.62 dB higher PSNR on ground datasets

Demonstrates superior efficiency over state-of-the-art methods

Abstract

High-quality novel view synthesis for large-scale scenes presents a challenging dilemma in 3D computer vision. Existing methods typically partition large scenes into multiple regions, reconstruct a 3D representation using Gaussian splatting for each region, and eventually merge them for novel view rendering. They can accurately render specific scenes, yet they do not generalize effectively for two reasons: (1) rigid spatial partition techniques struggle with arbitrary camera trajectories, and (2) the merging of regions results in Gaussian overlap to distort texture details. To address these challenges, we propose TraGraph-GS, leveraging a trajectory graph to enable high-precision rendering for arbitrarily large-scale scenes. We present a spatial partitioning method for large-scale scenes based on graphs, which incorporates a regularization constraint to enhance the rendering of textures and distant objects, as well as a progressive rendering strategy to mitigate artifacts caused by Gaussian overlap. Experimental results demonstrate its superior performance both on four aerial and four ground datasets and highlight its remarkable efficiency: our method achieves an average improvement of 1.86 dB in PSNR on aerial datasets and 1.62 dB on ground datasets compared to state-of-the-art approaches.