Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections
This addresses the problem of simplifying 3D imaging for applications like robotics or AR by leveraging common mirror reflections, though it is incremental in building on existing multi-view stereo methods.
The paper tackles 3D reconstruction from a single image by using mirror reflections as an auxiliary view, enabling multi-view stereo from a single capture and achieving robust 3D reconstruction with generalizable models.
Mirror reflections are common in everyday environments and can provide stereo information within a single capture, as the real and reflected virtual views are visible simultaneously. We exploit this property by treating the reflection as an auxiliary view and designing a transformation that constructs a physically valid virtual camera, allowing direct pixel-domain generation of the virtual view while adhering to the real-world imaging process. This enables a multi-view stereo setup from a single image, simplifying the imaging process, making it compatible with powerful feed-forward reconstruction models for generalizable and robust 3D reconstruction. To further exploit the geometric symmetry introduced by mirrors, we propose a symmetric-aware loss to refine pose estimation. Our framework also naturally extends to dynamic scenes, where each frame contains a mirror reflection, enabling efficient per-frame geometry recovery. For quantitative evaluation, we provide a fully customizable synthetic dataset of 16 Blender scenes, each with ground-truth point clouds and camera poses. Extensive experiments on real-world data and synthetic data are conducted to illustrate the effectiveness of our method.