对比度(视觉)
单眼
人工智能
计算机科学
基本事实
无监督学习
相似性(几何)
计算机视觉
过程(计算)
模式识别(心理学)
图像(数学)
操作系统
作者
Feng Cheng,Ye Wang,Yan-Hao Lai,Qiong Liu,Yijun Cao
标识
DOI:10.1117/1.jei.33.1.013019
摘要
In recent years, unsupervised learning has gained significant attention as a promising approach for monocular depth estimation. We propose an unsupervised monocular depth learning approach that combines self-teaching method and contrast-enhanced structural similarity (SSIM) loss. The self-teaching method involves learning from both a teacher and a student network. The teacher network generates a pseudo-ground truth depth map from non-augmented images and highest predicted resolution. The student network is trained on augmented images and related low resolution to supervise the training process. This approach allows the student network to learn from the teacher network and improves the quality of the depth predictions. In addition, we introduce a new contrast-enhanced version of the SSIM loss that improves the learning process by emphasizing the contrast between the predicted depth and the ground truth. Our experiments on the KITTI datasets demonstrate that our approach outperforms many unsupervised depth learning methods.
科研通智能强力驱动
Strongly Powered by AbleSci AI