{"ID":2825656,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.20017","arxiv_id":"2512.20017","title":"Scaling Point-based Differentiable Rendering for Large-scale Reconstruction","abstract":"Point-based Differentiable Rendering (PBDR) enables high-fidelity 3D scene reconstruction, but scaling PBDR to high-resolution and large scenes requires efficient distributed training systems. Existing systems are tightly coupled to a specific PBDR method. And they suffer from severe communication overhead due to poor data locality. In this paper, we present Gaian, a general distributed training system for PBDR. Gaian provides a unified API expressive enough to support existing PBDR methods, while exposing rich data-access information, which Gaian leverages to optimize locality and reduce communication. We evaluated Gaian by implementing 4 PBDR algorithms. Our implementations achieve high performance and resource efficiency: across six datasets and up to 128 GPUs, it reduces communication by up to 91% and improves training throughput by 1.50x-3.71x.","short_abstract":"Point-based Differentiable Rendering (PBDR) enables high-fidelity 3D scene reconstruction, but scaling PBDR to high-resolution and large scenes requires efficient distributed training systems. Existing systems are tightly coupled to a specific PBDR method. And they suffer from severe communication overhead due to poor...","url_abs":"https://arxiv.org/abs/2512.20017","url_pdf":"https://arxiv.org/pdf/2512.20017v1","authors":"[\"Hexu Zhao\",\"Xiaoteng Liu\",\"Xiwen Min\",\"Jianhao Huang\",\"Youming Deng\",\"Yanfei Li\",\"Ang Li\",\"Jinyang Li\",\"Aurojit Panda\"]","published":"2025-12-23T03:17:04Z","proceeding":"cs.DC","tasks":"[\"cs.DC\",\"cs.GR\"]","methods":"[]","has_code":false}