AI 译本 · Equalang
新上架PDF · 2026年11月翻译
加载中…
加载中…
arXiv · 2026
Solv3R：作为多视图求解器的 3D 循环 Transformer
Jeong-gi Kwak, Andrea Tagliasacchi, Sho Kagami, Yuki Ono et al.
Classical structure-from-motion reconstruction proceeds iteratively, refining camera poses and scene geometry from a current estimate. This allows maps to easily expand without recomputing already computed views, or geometry estimates to improve as more observations are provided. Most geometric foundation models, however, predict entire geometry in a single forward pass or update a recurrent state as frames arrive sequentially, making this expansion and refinement non-trivial. We introduce Solv3R, a looped transformer that learns to continue solving multi-view geometry from its current state. Importantly, its update operator is independent of the iteration count, allowing previously refined and newly introduced views to be jointly updated regardless of how ``solved'' they are. We train the operator to preserve accurate reconstructions under continued iteration and correct inaccurate states, enabling refinement of fixed image collections and integration of new observations. Representations of solved views can also be cached once and reused as geometric context across iterations, enabling compact and efficient key-value caching. We analyze the solver dynamics and compare it with the state-of-the-art, demonstrating that a single learned solver supports offline reconstruction, incremental reconstruction, relocalization, and streaming without task-specific training or modules. The code and models will be made publicly available at https://ubc-vision.github.io/solv3r/.
经典的运动恢复结构（SfM）重建采用迭代方式进行：从当前估计出发，不断优化相机位姿和场景几何。这使得地图能够轻松扩展，而无需重新计算已处理的视图；随着提供更多观测，几何估计也能得到改进。然而，大多数几何基础模型要么通过一次前向传播预测完整几何，要么在帧依次到达时更新循环状态，因此难以实现这种扩展与优化。我们提出 Solv3R，这是一种循环 Transformer，能够学习从当前状态继续求解多视图几何。重要的是，它的更新算子与迭代次数无关，因此无论先前视图已经“求解”到何种程度，都能与新引入的视图一同更新。我们训练该算子，使其在持续迭代过程中保持重建精度，并纠正不准确的状态，从而能够优化固定的图像集合并整合新的观测。已求解视图的表示还可以缓存一次，并在后续迭代中作为几何上下文重复使用，从而实现紧凑高效的键值缓存。我们分析了求解器的动态特性，并将其与当前最先进的方法进行比较。结果表明，单个学习型求解器无需针对特定任务进行训练或使用专用模块，即可支持离线重建、增量重建、重新定位和流式处理。代码和模型将公开发布于 https://ubc-vision.github.io/solv3r/。
PDF · 2026年11月翻译