Auto-regressive frameworks for next-scale prediction of 2D images have demonstrated strong potential for producing diverse and sophisticated content by progressively refining a coarse input. However, extending this paradigm to 3D object generation remains largely unexplored. In this paper, we introduce auto-regressive Gaussian splatting (ARGS), a framework for making next-scale predictions in parallel for generation according to levels of detail. We propose a Gaussian simplification strategy and reverse the simplification to guide next-scale generation. Benefiting from the use of hierarchical trees, the generation process requires only O(log n) steps, where n is the number of points. Furthermore, we propose a tree-based transformer to predict the tree structure auto-regressively, allowing leaf nodes to attend to their internal ancestors to enhance structural consistency. Extensive experiments demonstrate that our approach effectively generates multi-scale Gaussian representations with controllable levels of detail, visual fidelity, and a manageable time consumption budget.

Paper|Code

@InProceedings{Ruan_2026_CVPR,
    author    = {Ruan, Quanyuan and Shi, Kewei and Lei, Jiabao and Gao, Xifeng and Han, Xiaoguang},
    title     = {ARGS: Auto-Regressive Gaussian Splatting via Parallel Progressive Next-Scale Prediction},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings},
    month     = {June},
    year      = {2026},
    pages     = {8439-8448}
}