RIGOR：用于全向重建的刚性感知几何

中文摘要 AI 辅助

前馈式三维重建的最新进展使得模型能够仅从图像流中恢复稠密场景表示和相机运动。然而，此类预测在长轨迹上容易变得不一致，尤其是在具有重复结构、弱纹理和动态物体或人物的苛刻环境中。缓解这些挑战的一种方法是使用全向相机，它提供广泛的空间覆盖并捕获更丰富的视觉信息。然而，大多数模型不支持360度图像或需要额外的微调。为了弥合这两个方面，我们提出了RIGOR：一个用于重力对齐的全向视频的大规模重建流程，它保留冻结的前馈透视骨干，并将每个全景图利用为四视图虚拟刚性装置。刚性结构用于检测和修复局部不一致的预测，通过循环四视图共识检索闭环，并在全局优化前几何验证候选重访。验证的约束驱动一个Sim(3)位姿图，该图纠正序列中累积的旋转、平移和尺度漂移。我们证明，所提出的一致性机制在具有挑战性的建筑工地序列上，相比前馈基线，提高了轨迹精度和重建几何质量。代码可通过此链接获取：此https URL。

英文摘要

Recent developments in feed-forward 3D reconstruction resulted in models which can recover dense scene representations and camera motion solely from an image stream. However, such predictions are prone to becoming inconsistent over long trajectories, specifically in demanding environments with repetitive structures, weak textures and dynamic objects or people. One way to mitigate those challenges is to use an omnidirectional camera, which provides wide spatial coverage and captures richer visual information. Yet, the majority of models do not offer support for 360-degree imagery or require additional fine-tuning. To bridge these two aspects, we present RIGOR: a large-scale reconstruction pipeline for gravity-aligned omnidirectional videos that retains a frozen feed-forward perspective backbone and exploits each panorama as a four-view virtual rig. The rig structure is used to detect and repair locally inconsistent predictions, to retrieve loop closures through cyclic four-view consensus, and to geometrically verify candidate revisits before global optimization. Verified constraints drive a Sim(3) pose graph that corrects accumulated rotation, translation, and scale drift along the sequence. We demonstrate that the proposed consistency mechanisms improve both trajectory accuracy and reconstructed geometry over a feed-forward baseline on challenging construction-site sequences. The code is made available under this link: https://github.com/TangentH/RIGOR.

发表机构

• ETH Zürich（苏黎世联邦理工学院）
• Hilti AG（喜利得公司）

机构由 AI 辅助整理，请以论文原文为准。