Adaptive Multi-scale Cost Volume Construction and Aggregation for Stereo Matching

被引：1
|
作者：
Pang Y.-W. [1 ]
Su C. [1 ]
Long T. [1 ]
机构：
[1] School of Electrical and Information Engineering, Tianjin University, Tianjin
来源：
Dongbei Daxue Xuebao/Journal of Northeastern University | 2023年 / 44卷 / 04期
关键词：
adaptive aggregation; cost volume; feature enhancement; stereo matching;
D O I：
10.12068/j.issn.1005-3026.2023.04.001
中图分类号：
学科分类号：
摘要：
Stereo matching based on convolutional neural network has made great progress.Existing methods still suffer from mismatching in weak texture regions, details and edges.Based on the cost volume commonly used in stereo matching, a stereo matching network with adaptive multi-scale cost volume construction and aggregation was proposed.Firstly, the proposed method fully fused the multi-scale features to obtain the recombined features.Then, a learnable feature enhancement module was used to recover the detail information for multi-scale cost volumes.Finally, after intra-scale aggregation based on global attention, an adaptive multi-scale weighting method was proposed for inter-scale aggregation to screen the matching features adapted to the disparity regression of each scale.Massive experiments on the SceneFlow and KITTI2015 datasets show that the proposed method achieves competitive performance with smaller network size which verifies the effectiveness of the proposed method. © 2023 Northeastern University.All rights reserved.
引用
收藏
页码：457 / 468
页数：11
相关论文
共 17 条
  • [1] Zhao Q, Zhou B, Jia L I, Et al., A brief survey on virtual reality technology [J], Science and Technology Review, 34, 14, pp. 71-75, (2016)
  • [2] Chen C Y, Seff A, Kornhauser A, Et al., Deepdriving:learning affordance for direct perception in autonomous driving[C], Proceedings of the IEEE International Conference on Computer Vision, pp. 2722-2730, (2015)
  • [3] Oisel L, Memin E, Morin L, Et al., One-dimensional dense disparity estimation for three-dimensional reconstruction, IEEE Transactions on Image Processing, 12, 9, pp. 1107-1119, (2003)
  • [4] Li Jing-jiao, Ma Li, Wang Ai-xia, Et al., Stereo matching algorithm based on improved Patchmatch and slice sampling particle belief propagation [J], Journal of Northeastern University(Natural Science), 37, 5, pp. 609-613, (2016)
  • [5] Zhang Zhi-min, Qiao Jian-zhong, Lin Shu-kuan, Et al., A view reconstruction method based on deep network [J], Journal of Northeastern University(Natural Science), 41, 8, pp. 1065-1069, (2020)
  • [6] Chang J R, Chen Y S., Pyramid stereo matching network [C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410-5418, (2018)
  • [7] Deng H, Liao Q, Lu Z, Et al., Parallax contextual representations for stereo matching[C], Proceedings of the IEEE International Conference on Image Processing, pp. 3193-3197, (2021)
  • [8] Liang Z, Feng Y, Guo Y, Et al., Learning for disparity estimation through feature constancy[C], Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2811-2820, (2018)
  • [9] Huang Z, Norris T B, Wang P., ES-Net: an efficient stereo matching network [C], Proceedings of the IEEE International Conference on Intelligent Robots and Systems, (2021)
  • [10] Yang M, Wu F, Li W., RLStereo: real-time stereo matching based on reinforcement learning [J], IEEE Transactions on Image Processing, 30, pp. 9442-9455, (2021)
12