Perceptual Loss

Perceptual Loss is a type of loss function in deep learning that measures differences in high-level feature representations extracted from pretrained neural networks, rather than low-level pixel-wise differences, to better align with human visual perception in tasks such as image reconstruction.

468

Publications

62.7K

Citations

1.7K

Authors

531

Institutions

Publications per year

2017–2026

409

Authors

1.7K

  1. QC
    Qifeng Chen

    Hong Kong University of Science and Technology, Hong Kong SAR China

    7 publications · 725 citations

    7

    h-index

  2. RT
    Radu Timofte

    ETH Zurich, Switzerland

    6 publications · 1.1K citations

    6

    h-index

  3. CC
    Chen Change Loy

    Nanyang Technological University, Singapore

    6 publications · 1.6K citations

    6

    h-index

  4. IM
    Ilya Makarov

    National Research University Higher School of Economics, Russia

    6 publications · 170 citations

    6

    h-index

  5. LV
    Luc Van Gool

    ETH Zurich, Switzerland

    5 publications · 490 citations

    5

    h-index

1–5 of 1.7K

Venues

  1. arXiv (Cornell University)

    Repository · 61 publications · 7.6K citations

    29

    h-index

  2. IEEE Transactions on Image Processing

    17 publications · 3.9K citations

    17

    h-index

  3. 14

    h-index

  4. IEEE Access

    19 publications · 386 citations

    14

    h-index

  5. Remote Sensing

    7 publications · 302 citations

    7

    h-index

1–5