Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
This addresses the challenge of efficient and high-quality large-scale scene reconstruction for computer vision and graphics applications, representing a novel method rather than an incremental improvement.
The paper tackles the problem of large-scale 3D scene reconstruction by proposing MixGS, a holistic optimization framework that avoids the limitations of divide-and-conquer methods, achieving state-of-the-art rendering quality and competitive speed while enabling training on a single 24GB VRAM GPU.
Recent advances in 3D Gaussian Splatting have shown remarkable potential for novel view synthesis. However, most existing large-scale scene reconstruction methods rely on the divide-and-conquer paradigm, which often leads to the loss of global scene information and requires complex parameter tuning due to scene partitioning and local optimization. To address these limitations, we propose MixGS, a novel holistic optimization framework for large-scale 3D scene reconstruction. MixGS models the entire scene holistically by integrating camera pose and Gaussian attributes into a view-aware representation, which is decoded into fine-detailed Gaussians. Furthermore, a novel mixing operation combines decoded and original Gaussians to jointly preserve global coherence and local fidelity. Extensive experiments on large-scale scenes demonstrate that MixGS achieves state-of-the-art rendering quality and competitive speed, while significantly reducing computational requirements, enabling large-scale scene reconstruction training on a single 24GB VRAM GPU. The code will be released at https://github.com/azhuantou/MixGS.