让大图集3D重建突破显存限制，无需训练即可高效拼接
MERG3R: A Divide-and-Conquer Approach to Large-Scale Neural Visual Geometry
- 分而治之：把无序图像切分成重叠子集独立重建
- 全局对齐与置信加权优化，实现高质量整体模型
- 适配现有模型，大幅提升大场景重建的效率和规模
基于Transformer的神经视觉几何模型（如VGGT、Pi3）在3D重建任务中表现优异，但因依赖全注意力机制，受限于GPU显存，难以扩展至大规模无序图像集。我们提出MERG3R——一种无需训练的分治框架，使几何基础模型突破内存瓶颈。该方法先将无序图像重新排序并划分为重叠、几何多样化的子集，分别独立重建；再通过高效的全局对齐与置信加权束调整，融合局部结果生成全局一致的3D模型。框架具有模型无关性，可兼容现有神经几何模型。在7-Scenes、NRGBD、Tanks & Temples和Cambridge Landmarks等大规模数据集上，MERG3R consistently提升重建精度、内存效率与可扩展性，实现超出内存限制的数据集的高质量重建。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。