.png){kind=icon}
返回
Dual Guided Aggregation Network for Stereo Image Matching
.png){kind=icon}
OA
AI
DOI：10.3390/s22166111.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Stereo image dense matching, which plays a key role in 3D reconstruction, remains a challenging task in photogrammetry and computer vision. In addition to block-based matching, recent studies based on artificial neural networks have achieved great progress in stereo matching by using deep convolutional networks. This study proposes a novel network called a dual guided aggregation network (Dual-GANet), which utilizes both left-to-right and right-to-left image matchings in network design and training to reduce the possibility of pixel mismatch. Flipped training with a cost volume consistentization is introduced to realize the learning of invisible-to-visible pixel matching and left-right consistency matching. In addition, suppressed multi-regression is proposed, which suppresses unrelated information before regression and selects multiple peaks from a disparity probability distribution. The proposed dual network with the left-right consistent matching scheme can be applied to most stereo matching models. To estimate the performance, GANet, which is designed based on semi-global matching, was selected as the backbone with extensions and modifications on guided aggregation, disparity regression, and loss function. Experimental results on the SceneFlow and KITTI2015 datasets demonstrate the superiority of the Dual-GANet compared to related models in terms of average end-point-error (EPE) and pixel error rate (ER). The Dual-GANet with an average EPE performance = 0.418 and ER (>1 pixel) = 5.81% for SceneFlow and average EPE = 0.589 and ER (>3 pixels) = 1.76% for KITTI2005 is better than the backbone model with the average EPE performance of = 0.440 and ER (>1 pixel) = 6.56% for SceneFlow and average EPE = 0.790 and ER (>3 pixels) = 2.32% for KITTI2005.
Keyword:
dense image matching
deep learning
left-right consistency
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.2W
被引数:
20.9W
机构
引用论文
The occurrence of Spiraea crenata and other rare steppe plants in Pannonian graveyards.png)
Biologia
BiologiaIF0
PREAI
分享收藏Enhanced Soft 3D Reconstruction Method with an Iterative Matching Cost Update Using Object Surface ConsensusSENSORSOAAI
SENSORSIF3.5
OAAI分享收藏Angiotensin II-Induced Hypertension: Effects on Central and Peripheral Atrial Natriuretic Peptide.
OAAI
OAAI分享收藏
查看更多内容