1 code implementation • 9 Mar 2022 • Fei Sheng, Feng Xue, Yicong Chang, Wenteng Liang, Anlong Ming
In this paper, we model the majority of accuracy contrast between them as the difference of depth distribution, which we call "Distribution drift".
1 code implementation • 9 Mar 2022 • Yicong Chang, Feng Xue, Fei Sheng, Wenteng Liang, Anlong Ming
The high performance of RGB-D based road segmentation methods contrasts with their rare application in commercial autonomous driving, which is owing to two reasons: 1) the prior methods cannot achieve high inference speed and high accuracy in both ways; 2) the different properties of RGB and depth data are not well-exploited, limiting the reliability of predicted road.
1 code implementation • 26 Feb 2021 • Feng Xue, Junfeng Cao, Yu Zhou, Fei Sheng, Yankai Wang, Anlong Ming
However, two issues remain unresolved: (1) The deep feature encodes the wrong farthest region in a scene, which leads to a distorted 3D structure of the predicted depth; (2) The low-level features are insufficient utilized, which makes it even harder to estimate the depth near the edge with sudden depth change.