Name
Abstract | ||
|---|---|---|
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 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). |
Year | Venue | DocType |
|---|---|---|
2020 | AAAI | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhang Youmin | 1 | 0 | 0.34 |
| Yimin Chen | 2 | 17 | 4.87 |
| Bai Xiao | 3 | 470 | 48.67 |
| Jun Zhou | 4 | 48 | 15.65 |
| Kun Yu | 5 | 38 | 7.33 |
| Zhiwei Li | 6 | 1315 | 107.73 |
| Kuiyuan Yang | 7 | 435 | 24.67 |