Deep-Learning Assisted High-Resolution Binocular Stereo Depth Reconstruction
ICRA(2020)
摘要
This work presents dense stereo reconstruction using high-resolution images for infrastructure inspections. The state-of-the-art stereo reconstruction methods, both learning and non-learning ones, consume too much computational resource on high-resolution data. Recent learning-based methods achieve top ranks on most benchmarks. However, they suffer from the generalization issue due to lack of task-specific training data. We propose to use a less resource demanding non-learning method, guided by a learning-based model, to handle high-resolution images and achieve accurate stereo reconstruction. The deep-learning model produces an initial disparity prediction with uncertainty for each pixel of the down-sampled stereo image pair. The uncertainty serves as a self-measurement of its generalization ability and the perpixel searching range around the initially predicted disparity. The downstream process performs a modified version of the Semi-Global Block Matching method with the up-sampled perpixel searching range. The proposed deep-learning assisted method is evaluated on the Middlebury dataset and high-resolution stereo images collected by our customized binocular stereo camera. The combination of learning and non-learning methods achieves better performance on 12 out of 15 cases of the Middlebury dataset. In our infrastructure inspection experiments, the average 3D reconstruction error is less than 0.004m.
更多查看译文
关键词
Middlebury dataset,nonlearning method,infrastructure inspection,downstream process,stereo reconstruction methods,semiglobal block matching method,3D reconstruction error,infrastructure inspection experiments,customized binocular stereo camera,high-resolution stereo images,deep-learning assisted method,predicted disparity,perpixel searching range,down-sampled stereo image pair,initial disparity prediction,deep-learning model,accurate stereo reconstruction,learning-based model,resource demanding nonlearning method,task-specific training data,generalization issue,learning-based methods,high-resolution data,computational resource,infrastructure inspections,dense stereo reconstruction,assisted high-resolution binocular stereo depth reconstruction
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络