Hierarchical Vector-Quantized Variational Autoencoder and Vector Credibility Mechanism for High-Quality Image Inpainting

被引:0
|
作者
Li, Cheng [1 ]
Xu, Dan [1 ]
Chen, Kuai [2 ]
机构
[1] Yunnan Univ, Sch Informat Sci & Engn, Kunming 650106, Peoples R China
[2] Yunnan Univ, Sch Govt, Kunming 650106, Peoples R China
基金
中国国家自然科学基金;
关键词
image inpainting; VQ-VAE; vector credibility; codebook;
D O I
10.3390/electronics13101852
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Image inpainting infers the missing areas of a corrupted image according to the information of the undamaged part. Many existing image inpainting methods can generate plausible inpainted results from damaged images with the fast-developed deep-learning technology. However, they still suffer from over-smoothed textures or textural distortion in the cases of complex textural details or large damaged areas. To restore textures at a fine-grained level, we propose an image inpainting method based on a hierarchical VQ-VAE with a vector credibility mechanism. It first trains the hierarchical VQ-VAE with ground truth images to update two codebooks and to obtain two corresponding vector collections containing information on ground truth images. The two vector collections are fed to a decoder to generate the corresponding high-fidelity outputs. An encoder then is trained with the corresponding damaged image. It generates vector collections approximating the ground truth by the help of the prior knowledge provided by the codebooks. After that, the two vector collections pass through the decoder from the hierarchical VQ-VAE to produce the inpainted results. In addition, we apply a vector credibility mechanism to promote vector collections from damaged images and approximate vector collections from ground truth images. To further improve the inpainting result, we apply a refinement network, which uses residual blocks with different dilation rates to acquire both global information and local textural details. Extensive experiments conducted on several datasets demonstrate that our method outperforms the state-of-the-art ones.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Vector-Quantized Variational AutoEncoder for pansharpening
    Talbi, Farid
    Elmezouar, Miloud Chikr
    Boutellaa, Elhocine
    Alim, Fatiha
    INTERNATIONAL JOURNAL OF REMOTE SENSING, 2023, 44 (20) : 6329 - 6349
  • [2] Generating High-Quality F0 Embeddings Using the Vector-Quantized Variational Autoencoder
    Portes, David
    Horak, Ales
    TEXT, SPEECH, AND DIALOGUE, TSD 2024, PT II, 2024, 15049 : 139 - 148
  • [3] Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation
    Zhao, Zhe
    Qi, Mengshi
    Ma, Huadong
    COMPUTER VISION - ECCV 2024, PT XXIX, 2025, 15087 : 447 - 463
  • [4] Leveraging Vector-Quantized Variational Autoencoder Inner Metrics for Anomaly Detection
    Gangloff, Hugo
    Pham, Minh-Tan
    Courtrai, Luc
    Lefevre, Sebastien
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 435 - 441
  • [5] Vector-quantized Variational Autoencoder for Phase-aware Speech Enhancement
    Tuan Vu Ho
    Quoc Huy Nguyen
    Akagi, Masato
    Unoki, Masashi
    INTERSPEECH 2022, 2022, : 176 - 180
  • [6] Vector-Quantized Autoencoder With Copula for Collaborative Filtering
    Wang, Guanyu
    Zhong, Ting
    Xu, Xovee
    Zhang, Kunpeng
    Zhou, Fan
    Wang, Yong
    PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 3458 - 3462
  • [7] Quaternion Vector Quantized Variational Autoencoder
    Luo, Hui
    Liu, Xin
    Sun, Jian
    Zhang, Yang
    IEEE SIGNAL PROCESSING LETTERS, 2025, 32 : 151 - 155
  • [8] CRANK: AN OPEN-SOURCE SOFTWARE FOR NONPARALLEL VOICE CONVERSION BASED ON VECTOR-QUANTIZED VARIATIONAL AUTOENCODER
    Kobayashi, Kazuhiro
    Huang, Wen-Chin
    Wu, Yi-Chiao
    Tobing, Patrick Lumban
    Hayashi, Tomoki
    Toda, Tomoki
    2021 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP 2021), 2021, : 5934 - 5938
  • [9] Rethinking the Objectives of Vector-Quantized Tokenizers for Image Synthesis
    Gu, Yuchao
    Wang, Xintao
    Ge, Yixiao
    Shan, Ying
    Shou, Mike Zheng
    2024 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2024, 2024, : 7631 - 7640
  • [10] Bone-conducted Speech Enhancement Using Vector-quantized Variational Autoencoder and Gammachirp Filterbank Cepstral Coefficients
    Quoc-Huy Nguyen
    Unoki, Masashi
    2022 30TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO 2022), 2022, : 21 - 25