arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.07547cs.CV
收藏

RAFT-Stereo:用于立体匹配的多级递归场变换

RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching

Princeton University(普林斯顿大学)

Lahav Lipson, Zachary Teed, Jia Deng

摘要:

介绍了一种基于光流网络RAFT的新的立体校正深度架构RAFT-Stereo。我们引入了多级卷积GRU,它可以更有效地在图像中传播信息。RAFT-Stereo的修改版本可以执行精确的实时推理。RAFT-stereo在Middlebury排行榜上排名第一,在1 px误差上优于第二好的方法29%,并且优于ETH 3D双视图立体基准的所有已发表工作。代码可在https://github.com/princeton-vl/RAFT-Stereo上获得。

英文摘要:

We introduce RAFT-Stereo, a new deep architecture for rectified stereo based on the optical flow network RAFT. We introduce multi-level convolutional GRUs, which more efficiently propagate information across the image. A modified version of RAFT-Stereo can perform accurate real-time inference. RAFT-stereo ranks first on the Middlebury leaderboard, outperforming the next best method on 1px error by 29% and outperforms all published work on the ETH3D two-view stereo benchmark. Code is available at https://github.com/princeton-vl/RAFT-Stereo.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑