Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images

被引:127
|
作者
Nie, Lang [1 ,2 ]
Lin, Chunyu [1 ,2 ]
Liao, Kang [1 ,2 ]
Liu, Shuaicheng [3 ]
Zhao, Yao [1 ,2 ]
机构
[1] Beijing Jiaotong Univ, Inst Informat Sci, Beijing 100044, Peoples R China
[2] Beijing Key Lab Adv Informat Sci & Network Techno, Beijing 100044, Peoples R China
[3] Univ Elect Sci & Technol China, Sch Informat & Commun Engn, Chengdu 611731, Peoples R China
基金
中国国家自然科学基金;
关键词
Image stitching; Image reconstruction; Feature extraction; Image resolution; Estimation; Strain; Solid modeling; Computer vision; deep image stitching; deep homogrpahy estimation; HOMOGRAPHY;
D O I
10.1109/TIP.2021.3092828
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Traditional feature-based image stitching technologies rely heavily on feature detection quality, often failing to stitch images with few features or low resolution. The learning-based image stitching solutions are rarely studied due to the lack of labeled data, making the supervised methods unreliable. To address the above limitations, we propose an unsupervised deep image stitching framework consisting of two stages: unsupervised coarse image alignment and unsupervised image reconstruction. In the first stage, we design an ablation-based loss to constrain an unsupervised homography network, which is more suitable for large-baseline scenes. Moreover, a transformer layer is introduced to warp the input images in the stitching-domain space. In the second stage, motivated by the insight that the misalignments in pixel-level can be eliminated to a certain extent in feature-level, we design an unsupervised image reconstruction network to eliminate the artifacts from features to pixels. Specifically, the reconstruction network can be implemented by a low-resolution deformation branch and a high-resolution refined branch, learning the deformation rules of image stitching and enhancing the resolution simultaneously. To establish an evaluation benchmark and train the learning framework, a comprehensive real-world image dataset for unsupervised deep image stitching is presented and released. Extensive experiments well demonstrate the superiority of our method over other state-of-the-art solutions. Even compared with the supervised solutions, our image stitching quality is still preferred by users.
引用
收藏
页码:6184 / 6197
页数:14
相关论文
共 50 条
  • [31] Research on Unsupervised Feature Point Prediction Algorithm for Multigrid Image Stitching
    Li, Jun
    Chen, Yufeng
    Mu, Aiming
    SYMMETRY-BASEL, 2024, 16 (08):
  • [32] Development of Automated Image Stitching System for Radiographic Images
    Samsudin, Salbiah
    Adwan, Somaya
    Arof, H.
    Mokhtar, N.
    Ibrahim, F.
    JOURNAL OF DIGITAL IMAGING, 2013, 26 (02) : 361 - 370
  • [33] Development of Automated Image Stitching System for Radiographic Images
    Salbiah Samsudin
    Somaya Adwan
    H. Arof
    N. Mokhtar
    F. Ibrahim
    Journal of Digital Imaging, 2013, 26 : 361 - 370
  • [34] An Efficient Approach Towards Image Stitching in Aerial Images
    Rathnayake, R. M. N. B.
    Seneviratne, L.
    2018 3RD INTERNATIONAL CONFERENCE ON INFORMATION TECHNOLOGY RESEARCH (ICITR), 2018,
  • [35] UNSUPERVISED MULTIPLE-CHANGE DETECTION IN VHR OPTICAL IMAGES USING DEEP FEATURES
    Saha, Sudipan
    Bovolo, Francesca
    Bruzzone, Lorenzo
    IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 1902 - 1905
  • [36] Unsupervised Deep Embedded Clustering for High-Dimensional Visual Features of Fashion Images
    Malhi, Umar Subhan
    Zhou, Junfeng
    Yan, Cairong
    Rasool, Abdur
    Siddeeq, Shahbaz
    Du, Ming
    APPLIED SCIENCES-BASEL, 2023, 13 (05):
  • [37] Unsupervised Deep Clustering for Fashion Images
    Yan, Cairong
    Malhi, Umar Subhan
    Huang, Yongfeng
    Tao, Ran
    KNOWLEDGE MANAGEMENT IN ORGANIZATIONS, KMO 2019, 2019, 1027 : 85 - 96
  • [38] Automatic panoramic image stitching using invariant features
    Brown, Matthew
    Lowe, David G.
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2007, 74 (01) : 59 - 73
  • [39] Image Stitching Method Based on Global and Local Features
    Xu X.
    Yuan S.
    Wang J.
    Dai Y.
    Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology, 2022, 42 (05): : 502 - 510
  • [40] Automatic Microscopy Image Stitching Based on Geometry Features
    Zhang, Yi
    Pang, Baochuan
    Yu, Yuan
    Zhang, Caifang
    2013 6TH INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING (CISP), VOLS 1-3, 2013, : 927 - 931