Fast Fourier Convolution

By Lu Chi, Borui Jiang, Yadong Mu. 2020

764 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

High-Resolution Image Synthesis with Latent Diffusion Models (2021, methodology): “Our evaluation follows the protocol of LaMa [85], a recent inpainting model that introduces a specialized architecture relying on Fast Fourier Convolutions [8].”
Resolution-robust Large Mask Inpainting with Fourier Convolutions (2021, methodology): “Interestingly, sharing the same convolutions across all frequencies shifts the model towards scale equivariance [4] (Figures 5, 6).”
Wavelet Convolutions for Large Receptive Fields (2024, methodology): “In this experiment, we use MobilenetV2 [48] where each depth-wise convolution is replaced with RepLK [11], GFNet [45], FFC [4], and the proposed WTConv layer.”
Global Filter Networks for Image Classification (2021, methodology): “With the breakthroughs of CNNs in vision [14, 13], there are a variety of works that start to incorporate Fourier transform in some deep learning method [26, 50, 9, 24, 6] for vision tasks.”
Fourier Neural Operator for Parametric Partial Differential Equations (2020, background): “Our approach is therefore a natural choice for problems in computer vision where invariance to discretization crucial is important (Chi et al., 2020). x ∈ (0 , 1) .”
Inpaint Anything: Segment Anything Meets Image Inpainting (2023, methodology): “For our Inpaint Anything (IA), we investigated the use of a simple, single-stage approach LaMa [13] for mask-based inpainting, which is arguably good in generating repetitive visual structures by combining fast Fourier convolutions (FFCs) [1], perceptual loss [6], and an aggressive training mask gen”