郑州大学学报（工学版）2024，Vol.45Issue(4)：11-18,8.DOI:10.13705/j.issn.1671-6833.2024.04.003
基于轻量化深度卷积循环网络的MVS方法
MVS Method Based on Lightweight Deep Convolutional Recurrent Network
摘要
Abstract
Based on deep learning MVS methods,neural networks suffered from a large number of parameters and high GPU memory consumption.To address this issue,a lightweight deep convolutional recurrent network recurrent network-based MVS method was proposed.Firstly,the original images passed through a lightweight multi-scale fea-ture extraction network to obtain high-level semantic feature maps.Then,a sparse cost volume to reduce the com-putational workload was constructed.Next,GPU memory consumption was reduced by using a simple plane sweep-ing technique that utilized by a convolutional recurrent network for cost volume regularization.Finally,sparse depth maps were extended to dense depth maps using an extension module.With a refinement algorithm,the proposed approach achieved a certain level of accuracy.The proposed approach was compared to state-of-the-art methods on the DTU dataset including traditonal MVS methods Camp,Furu,Tola,and Gipuma,and also including deep learn-ing-based MVS methods SurfaceNet,PU-Net,MVSNet,R-MVSNet,Point-MVSNet,Fast-MVSNet,GBI-Net,and TransMVSNet.The results demonstrated that the proposed approach reduced GPU consumption to approximately 3.1 GB during the prediction stage,and the differences in precision compared to other methods were relatively small.关键词
轻量化/深度卷积循环网络/MVS方法/正则化/DTU数据集Key words
lightweight/deep convolutional recurrent network/MVS method/regularization/DTU dataset分类
信息技术与安全科学引用本文复制引用
佘维,孔祥基,郭淑明,田钊,李英豪..基于轻量化深度卷积循环网络的MVS方法[J].郑州大学学报（工学版）,2024,45(4):11-18,8.基金项目
嵩山实验室预研项目(YYYY022022003) （YYYY022022003）
国家自然科学基金资助项目(62206252) （62206252）
河南省科技攻关项目(212102310039) （212102310039）
