MERG3R：面向大规模神经视觉几何的分治方法
MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry
对做前馈式三维重建的人，这篇给出了一个免训练的分治推理范式：把无序大图集切成重叠子集分别用 VGGT/Pi3 类模型重建，再用全局对齐加置信度加权光束法平差合并，可直接套用到任何受显存限制的几何基础模型上以突破其原生规模上限。
原文依据 a training-free divide-and-conquer framework that enables geometric foundation models to operate far beyond their native memory limits
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神经视觉几何的进展，包括 VGGT 和 Pi3 等基于 Transformer 的模型，在三维重建任务上取得了令人瞩目的精度。然而，它们对全注意力的依赖使其从根本上受限于 GPU 显存容量，无法扩展到大规模、无序的图像集合。我们提出 MERG3R，一个免训练的分治框架，使几何基础模型能够远超其原生显存限制地运行。MERG3R 首先将无序图像重新排序并划分为相互重叠、几何上多样的子集，这些子集可以被独立重建。随后，它通过高效的全局对齐与置信度加权光束法平差流程合并所得的局部重建，生成全局一致的三维模型。该框架与模型无关，可与现有的神经几何模型搭配使用。在包括 7-Scenes、NRGBD、Tanks & Temples 和 Cambridge Landmarks 在内的大规模数据集上，MERG3R 持续提升了重建精度、显存效率与可扩展性，使得在数据集规模超出显存容量限制时仍能实现高质量重建。
英文原文摘要 1178 字符
Recent advancements in neural visual geometry, including transformer-based models such as VGGT and Pi3, have achieved impressive accuracy on 3D reconstruction tasks. However, their reliance on full attention makes them fundamentally limited by GPU memory capacity, preventing them from scaling to large, unordered image collections. We introduce MERG3R, a training-free divide-and-conquer framework that enables geometric foundation models to operate far beyond their native memory limits. MERG3R first reorders and partitions unordered images into overlapping, geometrically diverse subsets that can be reconstructed independently. It then merges the resulting local reconstructions through an efficient global alignment and confidence-weighted bundle adjustment procedure, producing a globally consistent 3D model. Our framework is model-agnostic and can be paired with existing neural geometry models. Across large-scale datasets--including 7-Scenes, NRGBD, Tanks & Temples, and Cambridge Landmarks--MERG3R consistently improves reconstruction accuracy, memory efficiency, and scalability, enabling high-quality reconstruction when the dataset exceeds memory capacity limits.