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
  • [1] Parallax-Tolerant Unsupervised Deep Image Stitching
    Nie, Lang
    Lin, Chunyu
    Liao, Kang
    Liu, Shuaicheng
    Zhao, Yao
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION, ICCV, 2023, : 7365 - 7374
  • [2] Unsupervised Deep Features for Privacy Image Classification
    Sitaula, Chiranjibi
    Xiang, Yong
    Aryal, Sunil
    Lu, Xuequan
    IMAGE AND VIDEO TECHNOLOGY (PSIVT 2019), 2019, 11854 : 404 - 415
  • [3] Efficient Unsupervised Image Stitching Using Attention Mechanism with Deep Homography Estimation
    Qin, Chunbin
    Ran, Xiaotian
    CMC-COMPUTERS MATERIALS & CONTINUA, 2024, 79 (01): : 1319 - 1334
  • [4] Deep Learning on Image Stitching With Multi-viewpoint Images: A Survey
    Ni Yan
    Yupeng Mei
    Ling Xu
    Huihui Yu
    Boyang Sun
    Zimao Wang
    Yingyi Chen
    Neural Processing Letters, 2023, 55 : 3863 - 3898
  • [5] IMAGE STITCHING OF DISSIMILAR IMAGES
    Rupert Licu, Gil
    John Mendoza, Nelvyn
    Kelvin See, Mark
    Sonam
    Noel Ochotorena, Carlo
    Antonette Roque, Maria
    Sybingco, Edwin
    2015 INTERNATIONAL CONFERENCE ON HUMANOID, NANOTECHNOLOGY, INFORMATION TECHNOLOGY,COMMUNICATION AND CONTROL, ENVIRONMENT AND MANAGEMENT (HNICEM), 2015, : 545 - +
  • [6] Deep Learning on Image Stitching With Multi-viewpoint Images: A Survey
    Yan, Ni
    Mei, Yupeng
    Xu, Ling
    Yu, Huihui
    Sun, Boyang
    Wang, Zimao
    Chen, Yingyi
    NEURAL PROCESSING LETTERS, 2023, 55 (04) : 3863 - 3898
  • [7] A Survey on Unsupervised Image Retrieval Using Deep Features
    Zhang H.
    Wu J.
    1829, Science Press (55): : 1829 - 1842
  • [8] GFA-UDIS: Global-to-Flow Alignment for Unsupervised Deep Image Stitching
    Han, Sijia
    Zhang, Zhibin
    MULTIMEDIA MODELING, MMM 2025, PT I, 2025, 15520 : 440 - 454
  • [9] Unsupervised Oral Endoscope Image Stitching Algorithm
    Huang R.
    Chang Q.
    Zhang Y.
    Journal of Shanghai Jiaotong University (Science), 2024, 29 (01) : 81 - 90
  • [10] Efficient unsupervised learning of biological images with compressed deep features
    Pastore, Vito Paolo
    Ciranni, Massimiliano
    Bianco, Simone
    Fung, Jennifer Carol
    Murino, Vittorio
    Odone, Francesca
    IMAGE AND VISION COMPUTING, 2023, 137