GHM Wavelet Transform for Deep Image Super Resolution
- URL: http://arxiv.org/abs/2204.07862v1
- Date: Sat, 16 Apr 2022 19:59:48 GMT
- Title: GHM Wavelet Transform for Deep Image Super Resolution
- Authors: Ben Lowe, Hadi Salman, Justin Zhan
- Abstract summary: The GHM multi-level discrete wavelet transform is proposed as preprocessing for image super resolution with convolutional neural networks.
37 single-level wavelets are experimentally analyzed from Haar, Daubechies, Biorthogonal, Reverse Biorthogonal, Coiflets, and Symlets wavelet families.
- Score: 4.522973196613816
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The GHM multi-level discrete wavelet transform is proposed as preprocessing
for image super resolution with convolutional neural networks. Previous works
perform analysis with the Haar wavelet only. In this work, 37 single-level
wavelets are experimentally analyzed from Haar, Daubechies, Biorthogonal,
Reverse Biorthogonal, Coiflets, and Symlets wavelet families. All single-level
wavelets report similar results indicating that the convolutional neural
network is invariant to choice of wavelet in a single-level filter approach.
However, the GHM multi-level wavelet achieves higher quality reconstructions
than the single-level wavelets. Three large data sets are used for the
experiments: DIV2K, a dataset of textures, and a dataset of satellite images.
The approximate high resolution images are compared using seven objective error
measurements. A convolutional neural network based approach using wavelet
transformed images has good results in the literature.
Related papers
- Local Implicit Wavelet Transformer for Arbitrary-Scale Super-Resolution [15.610136214020947]
Implicit neural representations have recently demonstrated promising potential in arbitrary-scale Super-Resolution (SR) of images.
Most existing methods predict the pixel in the SR image based on the queried coordinate and ensemble nearby features.
We propose the Local Implicit Wavelet Transformer (LIWT) to enhance the restoration of high-frequency texture details.
arXiv Detail & Related papers (2024-11-10T12:21:14Z) - WiNet: Wavelet-based Incremental Learning for Efficient Medical Image Registration [68.25711405944239]
Deep image registration has demonstrated exceptional accuracy and fast inference.
Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner.
We introduce a model-driven WiNet that incrementally estimates scale-wise wavelet coefficients for the displacement/velocity field across various scales.
arXiv Detail & Related papers (2024-07-18T11:51:01Z) - Hyper-VolTran: Fast and Generalizable One-Shot Image to 3D Object
Structure via HyperNetworks [53.67497327319569]
We introduce a novel neural rendering technique to solve image-to-3D from a single view.
Our approach employs the signed distance function as the surface representation and incorporates generalizable priors through geometry-encoding volumes and HyperNetworks.
Our experiments show the advantages of our proposed approach with consistent results and rapid generation.
arXiv Detail & Related papers (2023-12-24T08:42:37Z) - Exploring Invariance in Images through One-way Wave Equations [96.90549064390608]
In this paper, we empirically reveal an invariance over images-images share a set of one-way wave equations with latent speeds.
We demonstrate it using an intuitive encoder-decoder framework where each image is encoded into its corresponding initial condition.
arXiv Detail & Related papers (2023-10-19T17:59:37Z) - Wave-ViT: Unifying Wavelet and Transformers for Visual Representation
Learning [138.29273453811945]
Multi-scale Vision Transformer (ViT) has emerged as a powerful backbone for computer vision tasks.
We propose a new Wavelet Vision Transformer (textbfWave-ViT) that formulates the invertible down-sampling with wavelet transforms and self-attention learning.
arXiv Detail & Related papers (2022-07-11T16:03:51Z) - aiWave: Volumetric Image Compression with 3-D Trained Affine
Wavelet-like Transform [43.984890290691695]
Most commonly used volumetric image compression methods are based on wavelet transform, such as JP3D.
In this paper, we first design a 3-D trained wavelet-like transform to enable signal-dependent and non-separable transform.
Then, an affine wavelet basis is introduced to capture the various local correlations in different regions of volumetric images.
arXiv Detail & Related papers (2022-03-11T10:02:01Z) - Single Plane-Wave Imaging using Physics-Based Deep Learning [2.1410799064827226]
In plane-wave imaging, multiple unfocused ultrasound waves are transmitted into a medium of interest from different angles.
Deep learning methods have been proposed to improve ultrasound imaging.
We propose a data-to-image architecture that incorporates a wave-physics-based image formation algorithm in-between deep convolutional neural networks.
arXiv Detail & Related papers (2021-09-08T14:06:29Z) - Learning the geometry of wave-based imaging [24.531973107529584]
We build an interpretable neural architecture inspired by Fourier integral operators (FIOs) which approximate the wave physics.
We focus on learning the geometry of wave propagation captured by FIOs, which is implicit in the data, via a loss based on optimal transport.
The proposed FIONet performs significantly better than the usual baselines on a number of imaging inverse problems, especially in out-of-distribution tests.
arXiv Detail & Related papers (2020-06-10T14:29:54Z) - Noise Homogenization via Multi-Channel Wavelet Filtering for
High-Fidelity Sample Generation in GANs [47.92719758687014]
We propose a novel multi-channel wavelet-based filtering method for Generative Adversarial Networks (GANs)
When embedding a wavelet deconvolution layer in the generator, the resultant GAN, called WaveletGAN, takes advantage of the wavelet deconvolution to learn a filtering with multiple channels.
We conducted benchmark experiments on the Fashion-MNIST, KMNIST and SVHN datasets through an open GAN benchmark tool.
arXiv Detail & Related papers (2020-05-14T03:40:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.