Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching


  • Youmin Zhang Beihang University
  • Yimin Chen Beihang University
  • Xiao Bai Beihang University
  • Suihanjin Yu Beihang University
  • Kun Yu DeepMotion
  • Zhiwei Li DeepMotion
  • Kuiyuan Yang DeepMotion



State-of-the-art deep learning based stereo matching approaches treat disparity estimation as a regression problem, where loss function is directly defined on true disparities and their estimated ones. However, disparity is just a byproduct of a matching process modeled by cost volume, while indirectly learning cost volume driven by disparity regression is prone to overfitting since the cost volume is under constrained. In this paper, we propose to directly add constraints to the cost volume by filtering cost volume with unimodal distribution peaked at true disparities. In addition, variances of the unimodal distributions for each pixel are estimated to explicitly model matching uncertainty under different contexts. The proposed architecture achieves state-of-the-art performance on Scene Flow and two KITTI stereo benchmarks. In particular, our method ranked the 1st place of KITTI 2012 evaluation and the 4th place of KITTI 2015 evaluation (recorded on 2019.8.20). The codes of AcfNet are available at:




How to Cite

Zhang, Y., Chen, Y., Bai, X., Yu, S., Yu, K., Li, Z., & Yang, K. (2020). Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12926-12934.



AAAI Technical Track: Vision