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 across four aerial, four ground, and two cross-view (aerial-to-ground) datasets demonstrate the superior performance and remarkable efficiency of our method. Notably, utilizing only a single 24 GB GPU, our approach achieves average PSNR improvements of 0.36 dB, 1.24 dB, and 0.44 dB on large-scale aerial, ground, and cross-view datasets, respectively, compared to state-of-the-art approaches.