Skip to main content
placeholder image

Light weight stereo matching via deep extraction and integration of low and high level information

Conference Paper


Abstract


  • Deep convolutional neural networks (CNN) have demonstrated remarkable progress in stereo matching recently. However, disparity estimation in the ill-posed regions is still difficult. In addition, CNN based stereo matching methods often have impractical computational complexity and memory consumption. To address these problems we propose an end-to-end light weight CNN architecture to effectively learn and integrate low and high level information. To achieve this, a novel enhancement block built upon group convolution and dilated-convolution is proposed. Compared with state-of-the-art methods, the proposed method achieved competitive performance with the least number of network parameters on the Flyingthings3d and KITTI datasets.

UOW Authors


  •   Xu, Xianzhe (external author)
  •   Hou, Yonghong (external author)
  •   Wang, Pichao (external author)
  •   Jiang, Zhongyu (external author)
  •   Li, Wanqing

Publication Date


  • 2019

Citation


  • Xu, X., Hou, Y., Wang, P., Jiang, Z. & Li, W. (2019). Light weight stereo matching via deep extraction and integration of low and high level information. IEEE International Conference on Multimedia and Expo (ICME) 2019 (pp. 320-325). United States: IEEE.

Scopus Eid


  • 2-s2.0-85070963077

Start Page


  • 320

End Page


  • 325

Place Of Publication


  • United States

Abstract


  • Deep convolutional neural networks (CNN) have demonstrated remarkable progress in stereo matching recently. However, disparity estimation in the ill-posed regions is still difficult. In addition, CNN based stereo matching methods often have impractical computational complexity and memory consumption. To address these problems we propose an end-to-end light weight CNN architecture to effectively learn and integrate low and high level information. To achieve this, a novel enhancement block built upon group convolution and dilated-convolution is proposed. Compared with state-of-the-art methods, the proposed method achieved competitive performance with the least number of network parameters on the Flyingthings3d and KITTI datasets.

UOW Authors


  •   Xu, Xianzhe (external author)
  •   Hou, Yonghong (external author)
  •   Wang, Pichao (external author)
  •   Jiang, Zhongyu (external author)
  •   Li, Wanqing

Publication Date


  • 2019

Citation


  • Xu, X., Hou, Y., Wang, P., Jiang, Z. & Li, W. (2019). Light weight stereo matching via deep extraction and integration of low and high level information. IEEE International Conference on Multimedia and Expo (ICME) 2019 (pp. 320-325). United States: IEEE.

Scopus Eid


  • 2-s2.0-85070963077

Start Page


  • 320

End Page


  • 325

Place Of Publication


  • United States