Attention Aggregation Encoder-Decoder Network Framework for Stereo Matching

Zhang, Yaru; Li, Yaqian; Kong, Yating; Liu, Bin

doi:10.1109/lsp.2020.2993776

Cited by 19 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, research on domain adaptive models has become a hot topic. The network proposed in 35 used different branches and cross-stage contextual information to exploit features at various resolutions, and proposed a branch cross-stage encoding module to regularize the cost volume. EdgeStereo 36 explored the relationship between stereo and edge information in a unified learning model.…”

Section: Related Workmentioning

confidence: 99%

An application of stereo matching algorithm based on transfer learning on robots in multiple scenes

Bi,

Li,

Tong

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Robot vision technology based on binocular vision holds tremendous potential for development in various fields, including 3D scene reconstruction, target detection, and autonomous driving. However, current binocular vision methods used in robotics engineering have limitations such as high costs, complex algorithms, and low reliability of the generated disparity map in different scenes. To overcome these challenges, a cross-domain stereo matching algorithm for binocular vision based on transfer learning was proposed in this paper, named Cross-Domain Adaptation and Transfer Learning Network (Ct-Net), which has shown valuable results in multiple robot scenes. First, this paper introduces a General Feature Extractor to extract rich general feature information for domain adaptive stereo matching tasks. Then, a feature adapter is used to adapt the general features to the stereo matching network. Furthermore, a Domain Adaptive Cost Optimization Module is designed to optimize the matching cost. A disparity score prediction module was also embedded to adaptively adjust the search range of disparity and optimize the cost distribution. The overall framework was trained using a phased strategy, and ablation experiments were conducted to verify the effectiveness of the training strategy. Compared with the prototype PSMNet, on KITTI 2015 benchmark, the 3PE-fg of Ct-Net in all regions and non-occluded regions decreased by 19.3 and 21.1% respectively, meanwhile, on the Middlebury dataset, the proposed algorithm improves the sample error rate at least 28.4%, which is the Staircase sample. The quantitative and qualitative results obtained from Middlebury, Apollo, and other datasets demonstrate that Ct-Net significantly improves the cross-domain performance of stereo matching. Stereo matching experiments in real-world scenes have shown that it can effectively address visual tasks in multiple scenes.

show abstract

Section: Related Workmentioning

confidence: 99%

An application of stereo matching algorithm based on transfer learning on robots in multiple scenes

Bi,

Li,

Tong

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

An application of stereo matching algorithm based on transfer learning on robots in multiple scenarios

Wang

2023

Preprint

View full text Add to dashboard Cite

Robot vision technology based on binocular vision has significant potential for development in various fields, including 3D scenes and reconstruction, target detection, autonomous driving, and other fields. To date, current binocular vision methods used in robotics engineering suffer from high costs, complex algorithms, and low reliability of the generated disparity map in multiple scenarios. Robots require a cost-effective algorithm with cross-domain generalization capabilities for multiple scenarios. To address these issues, a cross-domain stereo matching algorithm for binocular vision based on transfer learning was proposed in this paper, named Cross-Domain Adaptation and Transfer Learning Network (Ct-Net), which has shown valuable results in multiple robot scenes. First, this paper introduces a General Feature Extractor (GFE) to extract rich general feature information for domain adaptive stereo matching tasks. Then, a feature adapter is used to adapt the general features to the stereo matching network. Furthermore, a Domain Adaptive Cost Optimization Module (DACOM) was designed to optimize the matching cost. A disparity score prediction module was also embedded to adaptively adjust the search range of disparity and optimize the cost distribution. The overall framework was trained using a phased strategy, and ablation experiments were conducted to verify the effectiveness of the training strategy. On KITTI 2015 benchmark, compared with the prototype PSMNet, the 3PE − fg of Ct-Net in all regions and non-occluded regions decreased by 19.3% and 21.1% respectively. On the Middlebury dataset, the 2PE of Ct-Net achieved comparable results on all samples. The quantitative and qualitative results obtained from Middlebury, Apollo, and other datasets demonstrate that Ct-Net significantly improves the cross-domain performance of stereo matching. Stereo matching experiments in real-world scenarios have shown that it can effectively address visual tasks in multiple robot scenes.

show abstract

“…Comparing with [9], we enhance the discriminability of cost feature, rather than the representation of the cost feature to the global scene. Due to the computational burden of spatial attention, [13] adds a channel attention module to each branch in order to learn uniform affinity for each channel for improving effective attention of high-level information. For AEM, we learn individual affinity for each cost feature for more explicit geometric meaning.…”

Section: Affinity Enhanced Modulementioning

confidence: 99%