多视图金字塔 Transformer：看得更粗，见得越广
Multi-view Pyramid Transformer: Look Coarser to See Broader
MVP 的局部到全局视图层级和细到粗空间层级为多视图 Transformer 提供了高效处理大量视图的通用架构，可直接用于前馈式三维重建与高斯泼溅初始化。
原文依据 a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds of images in a single forward pass
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论我们提出多视图金字塔 Transformer（MVP），一种可扩展的多视图 Transformer 架构，能在单次前向传播中直接从数十到数百张图像重建大型三维场景。借鉴“看得更广以见整体，看得更细以见细节”的思想，MVP 基于两个核心设计原则：1）局部到全局的视图间层级，逐步将模型视角从局部视图扩展到视图组，最终覆盖整个场景；2）细到粗的视图内层级，从精细的空间表示开始，逐步聚合成紧凑、信息密集的 token。这种双重层级实现了计算效率和表示丰富性，从而能够快速重建大型复杂场景。我们在多种数据集上验证了 MVP，并表明当与三维高斯泼溅作为底层三维表示结合时，它在各种视图配置下实现了最优的可泛化重建质量，同时保持高效率和可扩展性。
英文原文摘要 1086 字符
We propose Multi-view Pyramid Transformer (MVP), a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds of images in a single forward pass. Drawing on the idea of "looking broader to see the whole, looking finer to see the details," MVP is built on two core design principles: 1) a local-to-global inter-view hierarchy that gradually broadens the model's perspective from local views to groups and ultimately the full scene, and 2) a fine-to-coarse intra-view hierarchy that starts from detailed spatial representations and progressively aggregates them into compact, information-dense tokens. This dual hierarchy achieves both computational efficiency and representational richness, enabling fast reconstruction of large and complex scenes. We validate MVP on diverse datasets and show that, when coupled with 3D Gaussian Splatting as the underlying 3D representation, it achieves state-of-the-art generalizable reconstruction quality while maintaining high efficiency and scalability across a wide range of view configurations.