Multiview Stereo with Cascaded Epipolar RAFT-猫眼课题宝

DOI：

10.48550/arxiv.2205.04502

发表时间：

2022-05

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Zeyu Ma;Zachary Teed;Jia Deng

我们解决了多视点立体(MVS)，这是一个重要的3D视觉任务，从多个校准的图像重建3D模型，如密集的点云。提出了一种基于递归全对场变换(RAFT)结构的层叠外极浮筏多视立体(CER-MVS)方法。CER-MVS引入了RAFT的五个新变化：极地成本量、成本量级联、成本量多视角融合、动态监督和深度图的多分辨率融合。CER-MVS在多视点立体方面与以往的工作有很大的不同。与以往通过更新3D成本量来操作的工作不同，CER-MVS通过更新视差场来操作。此外，我们还提出了一种自适应阈值方法来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上获得了与之相当的性能(在已知结果中排名第二)，在TANKS-AND-TIMPLES基准测试(包括中级集和高级集)上获得了最先进的性能。代码可在https://github.com/princeton-vl/CER-MVS上找到

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

Multiview Stereo with Cascaded Epipolar RAFT

文献摘要

相似文献