Publications

(*) symbol indicates equal contribution.

  1. Imperceptible Protection against Style Imitation from Diffusion Models
    Namhyuk Ahn , Wonhyuk Ahn , KiYoon Yoo, Daesik Kim, and Seung-Hun Nam
    arXiv preprint arXiv:2403.19254, 2024
    arXiv
  2. DreamStyler: Paint by Style Inversion with Text-to-Image Diffusion Models
    Namhyuk Ahn, Junsoo Lee , Chunggi Lee , Kunhee Kim, Daesik Kim, Seung-Hun Nam, and Kibeom Hong
    In AAAI , 2024
    arXiv
  3. Data Augmentation for Low-Level Vision: CutBlur and Mixture-of-Augmentation
    Namhyuk Ahn, Jaejun Yoo, and Kyung-Ah Sohn
    International Journal of Computer Vision, 2024
    HTML
  4. Decomposing Texture and Semantics for Out-of-distribution Detection
    Jeong-Hyeon Moon*, Namhyuk Ahn*, and Kyung-Ah Sohn
    Expert Systems with Applications, 2024
    HTML
  5. DiffBlender: Scalable and Composable Multimodal Text-to-Image Diffusion Models
    Sungnyun Kim*, Junsoo Lee*, Kibeom Hong, Daesik Kim, and Namhyuk Ahn
    arXiv preprint arXiv:2305.15194, 2023
    arXiv
  6. Magnitude Attention-based Dynamic Pruning
    Jihye Back, Namhyuk Ahn , and Jangho Kim
    arXiv preprint arXiv:2306.05056, 2023
    arXiv
  7. AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks
    Kibeom Hong, Seogkyu Jeon, Junsoo Lee, Namhyuk Ahn , Kunhee Kim , Pilhyeon Lee, Daesik Kim, Youngjung Uh, and Hyeran Byun
    In ICCV , 2023
    arXiv
  8. Interactive Cartoonization with Controllable Perceptual Factors
    Namhyuk Ahn, Patrick Kwon, Jihye Back, Kibeom Hong , and Seungkwon Kim
    In CVPR , 2023
    arXiv
  9. LPMM: Intuitive Pose Control for Neural Talking-Head Model via Landmark-Parameter Morphable Model
    Kwangho Lee, Patrick Kwon , Myung Ki Lee, Namhyuk Ahn, and Junsoo Lee
    In CVPRW , 2023
    arXiv
  10. WebtoonMe: A Data-Centric Approach for Full-Body Portrait Stylization
    Jihye Back* , Seungkwon Kim*, and Namhyuk Ahn
    In SIGGRAPH Asia Technical Communications , 2022
    arXiv
  11. Efficient Deep Neural Network for Photo-Realistic Image Super-Resolution
    Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn
    Pattern Recognition, 2022
    arXiv
  12. Cross-Domain Style Mixing for Face Cartoonization
    Seungkwon Kim, Chaeheon Gwak , Dohyun Kim , Kwangho Lee, Jihye Back, Namhyuk Ahn, and Daesik Kim
    In CVPRW , 2022
    arXiv
  13. Exploiting Distortion Information for Multi-Degraded Image Restoration
    Wooksu Shin, Namhyuk Ahn, Jeong-Hyeon Moon, and Kyung-Ah Sohn
    In CVPRW , 2022
    PDF
  14. Toward an Efficient Deep Image Restoration Method
    Namhyuk Ahn
    PhD thesis. Ajou University , 2021
    PDF
  15. What is Wrong With One-Class Anomaly Detection?
    JuneKyu Park, Jeong-Hyeon Moon, Namhyuk Ahn, and Kyung-Ah Sohn
    In ICLRW , 2021
    arXiv
  16. Restoring Spatially-Heterogeneous Distortions Using Mixture of Experts Network
    Sijin Kim*, Namhyuk Ahn*, and Kyung-Ah Sohn
    In ACCV , 2020
    arXiv
  17. Rethinking Data Augmentation for Image Super-Resolution: A Comprehensive Analysis and a New Strategy
    Jaejun Yoo*, Namhyuk Ahn*, and Kyung-Ah Sohn
    In CVPR , 2020
    arXiv
  18. SimUSR: A Simple but Strong Baseline for Unsupervised Image Super-Resolution
    Namhyuk Ahn*, Jaejun Yoo*, and Kyung-Ah Sohn
    In CVPRW , 2020
    arXiv
  19. Fast, Accurate, and Lightweight Super-Resolution With Cascading Residual Network
    Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn
    In ECCV , 2018
    arXiv
  20. Image Super-Resolution via Progressive Cascading Residual Network
    Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn
    In CVPRW , 2018
    PDF
  21. Image Distortion Detection Using Convolutional Neural Network
    Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn
    In ACPR , 2017
    arXiv