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

2025-06-10

AI Summary

To address two key challenges in large-scale novel view synthesis—rigid spatial partitioning failing to adapt to arbitrary camera trajectories, and region fusion causing Gaussian overlap and texture distortion—this paper proposes a trajectory-guided, spatially adaptive Gaussian splatting method. Our approach features: (1) a camera-trajectory graph structure enabling dynamic, semantic-aware spatial partitioning; (2) graph-regularized optimization that jointly enforces long-range geometric consistency and local texture fidelity; and (3) a progressive rendering strategy that explicitly suppresses Gaussian overlap artifacts. Evaluated on four aerial and four ground-level large-scale datasets, our method achieves average PSNR gains of 1.86 dB and 1.62 dB, respectively, significantly outperforming state-of-the-art methods. It delivers superior accuracy, strong generalization across diverse trajectory patterns, and computational efficiency.

Technology Category

• Computer Vision: Computational Photography, Image & Video Synthesis
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Data transparency and provenance

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.

Problem

• Rendering large-scale scenes with arbitrary camera trajectories
• Avoiding Gaussian overlap distortion in merged 3D representations
• Improving texture and distant object rendering accuracy

Innovation

• Trajectory graph-based spatial partitioning method
• Regularization constraint enhances texture rendering
• Progressive rendering reduces Gaussian overlap artifacts