Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in matching tasks. However, all-pairs correlations lack non-local geometry knowledge and have difficulties tackling local ambiguities in ill-posed regions. In this paper, we propose Iterative Geometry Encoding Volume (IGEV-Stereo), a new deep network architecture for stereo matching. The proposed IGEV-Stereo builds a combined geometry encoding volume that encodes geometry and context information as well as local matching details, and iteratively indexes it to update the disparity map. To speed up the convergence, we exploit GEV to regress an accurate starting point for ConvGRUs iterations. On KITTI 2015, IGEV-Stereo ranks $1^{st}$ among all published methods and is the fastest among the top 10 methods. In addition, IGEV-Stereo has strong cross-dataset generalization as well as high inference efficiency. We also extend our IGEV to multi-view stereo (MVS), i.e. IGEV-MVS, which achieves competitive accuracy on DTU benchmark. Code is available at https://github.com/gangweiX/IGEV.

本文提出了一种新的深度网络结构IGEV-Stereo，其利用综合几何编码体来编码几何、上下文信息以及本地匹配细节，通过迭代地索引来更新视差图，同时利用GEV来回归卷积GRU的精确起点，以加速收敛。IGEV-Stereo在KITTI 2015和2012（反射）的所有已发布方法中排名第1，并且是排名前10的方法中最快的。此外，IGEV-Stereo具有强的跨数据集泛化性以及高的推断效率。我们还将我们的IGEV扩展到多视角立体（MVS），即IGEV-MVS，在DTU基准测试中实现了竞争性的准确性。

迭代几何编码体积用于立体匹配