Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching
This addresses overfitting in stereo matching for computer vision applications, offering an incremental improvement by adding constraints to existing cost volume methods.
The paper tackles the problem of overfitting in deep stereo matching by directly constraining the cost volume with unimodal distributions peaked at true disparities and estimating variances to model uncertainty, achieving state-of-the-art performance with 1st place on KITTI 2012 and 4th place on KITTI 2015 benchmarks.
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 $1^{st}$ place of KITTI 2012 evaluation and the $4^{th}$ place of KITTI 2015 evaluation (recorded on 2019.8.20). The codes of AcfNet are available at: https://github.com/DeepMotionAIResearch/DenseMatchingBenchmark.