Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces Auto-Regressive Gaussian Splatting (ARGS), a novel framework for parallel next-scale prediction of 3D objects using Gaussian splatting. ARGS leverages a Gaussian simplification strategy and its reverse to guide the generation process across multiple levels of detail, achieving \(\mathcal{O}(\log n)\) complexity through hierarchical trees. A tree-based transformer is proposed to predict the tree structure auto-regressively, enhancing structural consistency by enabling leaf nodes to attend to their internal ancestors.
Generate high-fidelity 3D objects with controllable levels of detail in logarithmic time using a novel auto-regressive Gaussian splatting framework.
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.