论文标题
具有级联的对异性筏的多视立体声
Multiview Stereo with Cascaded Epipolar RAFT
论文作者
论文摘要
我们谈到多视立体声（MVS），这是一个重要的3D视觉任务，该任务重建了3D模型，例如来自多个校准图像的密集点云。我们提出了CER-MVS（级联的Epolar Raft Multiview Stereo），这是一种基于用于光学流量的木筏（经常性的全对场变换）架构的新方法。 CER-MV引入了筏的五个新变化：面积成本量，成本量级联，成本量的多视图融合，动态监督和深度图的多解析融合。 CER-MV与多视立体声的先前工作明显不同。与先前的工作不同，该工作通过更新3D成本量来运行，CER-MVS通过更新差异字段来运行。此外，我们提出了一种自适应阈值方法，以平衡重建点云的完整性和准确性。实验表明，我们的方法在DTU（已知结果中的第二好）和Tanks-and-templass基准（中级和高级设置）上的最先进性能达到了竞争性能。代码可从https://github.com/princeton-vl/cer-mvs获得
We address multiview stereo (MVS), an important 3D vision task that reconstructs a 3D model such as a dense point cloud from multiple calibrated images. We propose CER-MVS (Cascaded Epipolar RAFT Multiview Stereo), a new approach based on the RAFT (Recurrent All-Pairs Field Transforms) architecture developed for optical flow. CER-MVS introduces five new changes to RAFT: epipolar cost volumes, cost volume cascading, multiview fusion of cost volumes, dynamic supervision, and multiresolution fusion of depth maps. CER-MVS is significantly different from prior work in multiview stereo. Unlike prior work, which operates by updating a 3D cost volume, CER-MVS operates by updating a disparity field. Furthermore, we propose an adaptive thresholding method to balance the completeness and accuracy of the reconstructed point clouds. Experiments show that our approach achieves competitive performance on DTU (the second best among known results) and state-of-the-art performance on the Tanks-and-Temples benchmark (both the intermediate and advanced set). Code is available at https://github.com/princeton-vl/CER-MVS
