利用镜面反射实现单图三维重建，无需多视角
Reflect3r: Single-View 3D Stereo Reconstruction Aided by Mirror Reflections
- 将镜中虚像当作辅助视图，构建物理上合法的虚拟相机
- 在真实场景和合成数据上均实现高精度3D重建，优于传统方法
- 适合需要快速重建的动态场景或移动设备应用
镜面反射在日常环境中普遍存在，能在单次拍摄中同时提供真实与虚像视图，蕴含立体信息。本文将反射视为辅助视图，设计一种变换以构建符合物理成像过程的虚拟相机，实现像素级直接生成虚拟视图。由此可在单图基础上模拟多视角立体重建，简化成像流程，并兼容高效的前馈重建模型，实现泛化性强、鲁棒性高的三维重建。为进一步利用镜面对称带来的几何约束，提出对称感知损失以优化位姿估计。该框架自然拓展至动态场景，每帧包含镜面反射时可实现逐帧几何恢复。为量化评估，我们构建了一个由16个Blender场景组成的全可定制合成数据集，每个场景配备真值点云和相机位姿。在真实世界与合成数据上的大量实验验证了方法的有效性。
原文摘要 · Abstract (English)
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.
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。