Corpus ID: 208268566

Pixel Adaptive Filtering Units

@article{Kokkinos2019PixelAF,
  title={Pixel Adaptive Filtering Units},
  author={Filippos Kokkinos and Ioannis Marras and Matteo Maggioni and Gregory G. Slabaugh and Stefanos Zafeiriou},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.10581}
}
  • Filippos Kokkinos, Ioannis Marras, +2 authors Stefanos Zafeiriou
  • Published in ArXiv 2019
  • Computer Science
  • State-of-the-art methods for computer vision rely heavily on the translation equivariance and spatial sharing properties of convolutional layers without explicitly taking into consideration the input content. Modern techniques employ deep sophisticated architectures in order to circumvent this issue. In this work, we propose a Pixel Adaptive Filtering Unit (PAFU) which introduces a differentiable kernel selection mechanism paired with a discrete, learnable and decorrelated group of kernels to… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 44 REFERENCES

    RAISR: Rapid and Accurate Image Super Resolution

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Enhanced Deep Residual Networks for Single Image Super-Resolution

    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    A non-local algorithm for image denoising

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Convolutional Networks with Adaptive Inference Graphs

    VIEW 1 EXCERPT

    Iterative Joint Image Demosaicking and Denoising Using a Residual Denoising Network

    VIEW 3 EXCERPTS

    Pixel-Adaptive Convolutional Neural Networks

    VIEW 2 EXCERPTS

    Neural Nearest Neighbors Networks

    VIEW 2 EXCERPTS

    BLADE: Filter learning for general purpose computational photography

    VIEW 1 EXCERPT

    Burst Denoising with Kernel Prediction Networks

    VIEW 2 EXCERPTS