WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting
This addresses the need for a unified and efficient 3D reconstruction method for computer vision applications, though it appears incremental as it builds on existing priors and tasks.
The paper tackles the problem of versatile 3D geometric prediction by introducing WorldMirror, a feed-forward model that integrates diverse geometric priors to generate multiple 3D representations, achieving state-of-the-art performance across various benchmarks.
We present WorldMirror, an all-in-one, feed-forward model for versatile 3D geometric prediction tasks. Unlike existing methods constrained to image-only inputs or customized for a specific task, our framework flexibly integrates diverse geometric priors, including camera poses, intrinsics, and depth maps, while simultaneously generating multiple 3D representations: dense point clouds, multi-view depth maps, camera parameters, surface normals, and 3D Gaussians. This elegant and unified architecture leverages available prior information to resolve structural ambiguities and delivers geometrically consistent 3D outputs in a single forward pass. WorldMirror achieves state-of-the-art performance across diverse benchmarks from camera, point map, depth, and surface normal estimation to novel view synthesis, while maintaining the efficiency of feed-forward inference. Code and models will be publicly available soon.