We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses the metric 3D scene geometry and cameras. MapAnything leverages a factored representation of multi-view scene geometry, i.e., a collection of depth maps, local ray maps, camera poses, and a metric scale factor that effectively upgrades local reconstructions into a globally consistent metric frame. Standardizing the supervision and training across diverse datasets, along with flexible input augmentation, enables MapAnything to address a broad range of 3D vision tasks in a single feed-forward pass, including uncalibrated structure-from-motion, calibrated multi-view stereo, monocular depth estimation, camera localization, depth completion, and more. We provide extensive experimental analyses and model ablations demonstrating that MapAnything outperforms or matches specialist feed-forward models while offering more efficient joint training behavior, thus paving the way toward a universal 3D reconstruction backbone.

翻译：我们提出MapAnything，一种基于Transformer的统一前馈模型，该模型接收单张或多张图像以及可选的几何输入（如相机内参、位姿、深度或部分重建结果），并直接回归出度量化的三维场景几何与相机参数。MapAnything采用多视图场景几何的分解式表示，即一组深度图、局部射线图、相机位姿以及一个度量尺度因子，从而有效地将局部重建升级至全局一致的度量坐标系。通过对多样化数据集进行标准化监督训练，并结合灵活的输入增强，MapAnything能够在单次前馈推理中处理广泛的三维视觉任务，包括未标定的运动恢复结构、已标定的多视图立体视觉、单目深度估计、相机定位、深度补全等。我们提供了广泛的实验分析与模型消融研究，结果表明MapAnything在性能上优于或匹配专用前馈模型，同时展现出更高效的联合训练特性，从而为构建通用三维重建主干网络开辟了道路。