面向前馈高斯泼溅的 Z-Order Transformer
Z-Order Transformer for Feed-Forward Gaussian Splatting
将无序高斯点集通过 Z-order 曲线序列化，并用稀疏注意力建模空间与语义关系，为前馈式 3DGS 提供了一种可复用的高效上下文建模与冗余压缩方案。
原文依据 sparse attention mechanism, enabled by a Z-order strategy that organizes the unstructured Gaussian set into a spatially coherent sequence
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期三维高斯泼溅（3DGS）的进展推动了逼真新视角合成的显著进步。然而，传统 3DGS 依赖缓慢的迭代优化过程，限制了其在需要实时结果的场景中的应用。为克服这一瓶颈，近期前馈方法旨在直接从图像预测高斯属性，但往往受困于高斯基元的冗余与渲染质量。本文提出一种专为前馈高斯泼溅设计的 Transformer 架构。我们的关键洞见是：通过稀疏注意力机制可有效捕获高斯之间的空间与语义关系，该机制由 Z-order 策略实现，将无结构的高斯集合组织为空间连贯的序列。此外，我们引入该 Z-order 策略以自适应地抑制冗余，同时保留关键结构细节。这使得 Transformer 能够在单次前向传播中高效建模上下文、压缩高斯基元并预测高斯属性。综合实验表明，我们的方法以更少的高斯基元实现了快速且高质量的新视角合成。
英文原文摘要 1250 字符
Recent advances in 3D Gaussian Splatting (3DGS) have enabled significant progress in photorealistic novel view synthesis. However, traditional 3DGS relies on a slow, iterative optimization process, which limits its use in scenarios demanding real-time results. To overcome this bottleneck, recent feed-forward methods aim to predict Gaussian attributes directly from images, but they often struggle with the redundancy of Gaussian primitives and rendering quality. In this paper, we introduce a transformer-based architecture specifically designed for feed-forward Gaussian Splatting. Our key insight is that spatial and semantic relationships among Gaussians can be effectively captured through a sparse attention mechanism, enabled by a Z-order strategy that organizes the unstructured Gaussian set into a spatially coherent sequence. Furthermore, we incorporate this Z-order strategy to adaptively suppress redundancy while preserving critical structural details. This allows the transformer to efficiently model context, compress Gaussian primitives, and predict Gaussian attributes in a single forward pass. Comprehensive experiments demonstrate that our method achieves fast and high-quality novel view synthesis with fewer Gaussian primitives.