Related papers: Fourier-CPPNs for Image Synthesis

Feature pyramids are widely exploited in many detectors to solve the scale variation problem for object detection. In this paper, we first investigate the Feature Pyramid Network (FPN) architectures and briefly categorize them into three…

Feature pyramid network (FPN) based models, which fuse the semantics and salient details in a progressive manner, have been proven highly effective in salient object detection. However, it is observed that these models often generate…

Deep generative models allow for photorealistic image synthesis at high resolutions. But for many applications, this is not enough: content creation also needs to be controllable. While several recent works investigate how to disentangle…

Digital cameras and displays utilise picture elements (pixels) that perform a single function: detecting or emitting light intensity. To exploit the full information content of electromagnetic waves, more advanced elements are required.…

We propose a new network architecture, the Fractal Pyramid Networks (PFNs) for pixel-wise prediction tasks as an alternative to the widely used encoder-decoder structure. In the encoder-decoder structure, the input is processed by an…

Superpixels are a useful representation to reduce the complexity of image data. However, to combine superpixels with convolutional neural networks (CNNs) in an end-to-end fashion, one requires extra models to generate superpixels and…

We introduce the hierarchical compositional network (HCN), a directed generative model able to discover and disentangle, without supervision, the building blocks of a set of binary images. The building blocks are binary features defined…

Image compositing is a method used to generate realistic yet fake imagery by inserting contents from one image to another. Previous work in compositing has focused on improving appearance compatibility of a user selected foreground segment…

In this work we describe a Convolutional Neural Network (CNN) to accurately predict the scene illumination. Taking image patches as input, the CNN works in the spatial domain without using hand-crafted features that are employed by most…

Dense pixel matching is required for many computer vision algorithms such as disparity, optical flow or scene flow estimation. Feature Pyramid Networks (FPN) have proven to be a suitable feature extractor for CNN-based dense matching tasks.…

Machine learning applied to computer vision and signal processing is achieving results comparable to the human brain on specific tasks due to the great improvements brought by the deep neural networks (DNN). The majority of state-of-the-art…

Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting…

In this paper, we present a novel image inpainting technique using frequency domain information. Prior works on image inpainting predict the missing pixels by training neural networks using only the spatial domain information. However,…

Most existing neural networks for learning graphs address permutation invariance by conceiving of the network as a message passing scheme, where each node sums the feature vectors coming from its neighbors. We argue that this imposes a…

Existing methods for scene text detection can be divided into two paradigms: segmentation-based and anchor-based. While Segmentation-based methods are well-suited for irregular shapes, they struggle with compact or overlapping layouts.…

In computer vision, characteristics refer to image regions with unique properties, such as corners, edges, textures, or areas with high contrast. These regions can be represented through feature points (FPs). FP detection and description…

Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant. However, in some instances, such as change detection in…

Deep learning has been widely used for hyperspectral pixel classification due to its ability of generating deep feature representation. However, how to construct an efficient and powerful network suitable for hyperspectral data is still…

Generative Adversarial Networks (GANs) are proving to be a powerful indirect genotype-to-phenotype mapping for evolutionary search, but they have limitations. In particular, GAN output does not scale to arbitrary dimensions, and there is no…

An analysis of CPN models is given in terms of general coordinates or arbitrary interpolating fields.Only closed expressions made from simple functions are involved.Special attention is given to CP2 and CP4. In the first of these the…