MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Abstract

MapAnything is 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 directly regresses metric 3D scene geometry and cameras. It leverages a factored representation of multi-view scene geometry to address a broad range of 3D vision tasks in a single feed-forward pass, including uncalibrated structure-from-motion, calibrated multi-view stereo, and monocular depth estimation, matching or outperforming specialist models.