Related papers: Fourier Image Transformer

Fourier domain structured low-rank matrix priors are emerging as powerful alternatives to traditional image recovery methods such as total variation and wavelet regularization. These priors specify that a convolutional structured matrix,…

Recently, much advance has been made in image captioning, and an encoder-decoder framework has been adopted by all the state-of-the-art models. Under this framework, an input image is encoded by a convolutional neural network (CNN) and then…

Modern deep learning systems are increasingly deployed in situations such as personalization and federated learning where it is necessary to support i) learning on small amounts of data, and ii) communication efficient distributed training…

Image identification is one of the most challenging tasks in different areas of computer vision. Scale-invariant feature transform is an algorithm to detect and describe local features in images to further use them as an image matching…

We address the problem of cross-domain image registration, where paired images exhibit coupled geometric misalignment and domain-specific appearance shift. We formalize this as a factorization problem: decomposing each image into a…

In recent years, deep neural networks have played a major role solving various challenges in two dimensional image processing.Fully Convolutional Networks (FCN) such as U-net have been shown to be highly successful at segmentation tasks for…

Deep learning surrogate models have shown promise in solving partial differential equations (PDEs). Among them, the Fourier neural operator (FNO) achieves good accuracy, and is significantly faster compared to numerical solvers, on a…

In recent computer vision research, the advent of the Vision Transformer (ViT) has rapidly revolutionized various architectural design efforts: ViT achieved state-of-the-art image classification performance using self-attention found in…

Neuroevolution has yet to scale up to complex reinforcement learning tasks that require large networks. Networks with many inputs (e.g. raw video) imply a very high dimensional search space if encoded directly. Indirect methods use a more…

Image inpainting involves filling missing areas of a corrupted image. Despite impressive results have been achieved recently, restoring images with both vivid textures and reasonable structures remains a significant challenge. Previous…

Image computation is a fundamental tool for performance assessment of astronomical instrumentation, usually implemented by Fourier transform techniques. We review the numerical implementation, evaluating a direct implementation of the…

One of the most efficient ways to produce unconditional simulations is with the kernel convolution using fast Fourier transform (FFT) [1]. However, when data is located on a surface, this approach is not efficient because data needs to be…

We propose an end-to-end image compression and analysis model with Transformers, targeting to the cloud-based image classification application. Instead of placing an existing Transformer-based image classification model directly after an…

We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a…

Recently, implicit neural representations (INR) have made significant strides in various vision-related domains, providing a novel solution for Multispectral and Hyperspectral Image Fusion (MHIF) tasks. However, INR is prone to losing…

Video prediction is a pixel-level task that generates future frames by employing the historical frames. There often exist continuous complex motions, such as object overlapping and scene occlusion in video, which poses great challenges to…

Nature is infinitely resolution-free. In the context of this reality, existing diffusion models, such as Diffusion Transformers, often face challenges when processing image resolutions outside of their trained domain. To overcome this…

We propose a new image denoising algorithm, dubbed as Fully Convolutional Adaptive Image DEnoiser (FC-AIDE), that can learn from an offline supervised training set with a fully convolutional neural network as well as adaptively fine-tune…

Image segmentation is a popular area of research in computer vision that has many applications in automated image processing. A recent technique called piecewise flat embeddings (PFE) has been proposed for use in image segmentation; PFE…

Facade parsing stands as a pivotal computer vision task with far-reaching applications in areas like architecture, urban planning, and energy efficiency. Despite the recent success of deep learning-based methods in yielding impressive…