Laser & Optoelectronics Progress, Volume. 59, Issue 18, 1815005(2022)
Binocular Depth Estimation Algorithm Based on Multi-Scale Attention Feature Fusion
Fig. 1. Overall structure of multi-scale attention fusion network
Fig. 2. Group-related attention fusion module
Fig. 3. Multi-scale convolution global attention module
Fig. 4. 3D channel attention aggregation module
Fig. 5. Parallax maps obtained by different algorithms on SceneFlow dataset
Fig. 6. Visualization results of ablation experiment on KITTI2015 test set
Fig. 7. Qualitative evaluation results of different networks on KITTI2015 dataset
Fig. 8. Qualitative evaluation results of different networks on KITTI2012 dataset
Fig. 9. Qualitative evaluation results of different networks on Middlebury-v3 dataset
|
|
|
|
|
Get Citation
Copy Citation Text
Huitong Yang, Liang Lei, Yongchun Lin. Binocular Depth Estimation Algorithm Based on Multi-Scale Attention Feature Fusion[J]. Laser & Optoelectronics Progress, 2022, 59(18): 1815005
Category: Machine Vision
Received: Jul. 15, 2021
Accepted: Jul. 20, 2021
Published Online: Aug. 29, 2022
The Author Email: Lei Liang (leiliang@gdut.edu.cn)