ARGS: Auto-Regressive Gaussian Splatting via Parallel Progressive Next-Scale Prediction

View PDF HTML (experimental)

Abstract: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 (\mathcal{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.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2604.00494 [cs.CV]

(or arXiv:2604.00494v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2604.00494

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Quanyuan Ruan [view email] [v1] Wed, 1 Apr 2026 05:21:59 UTC (22,413 KB)