Paul L. Rosin

Cardiff University | CU · School of Computer Science and Informatics

Geometric estimation is required for scene understanding and analysis in panoramic 360{\deg} images. Current methods usually predict a single feature, such as depth or surface normal. These methods can lack robustness, especially when dealing with intricate textures or complex object surfaces. We introduce a novel multi-task learning (MTL) network...

Visual perception of ships has been attracting increasing attention in the fields of computer vision and ocean engineering. Despite the extensive work related to landmark detection of common objects, the role of landmarks in ship perception has been overlooked. In this paper, we aim to fill this gap by focusing on ship landmarks. Specifically, we g...

Stroke-based Rendering (SBR) aims to decompose an input image into a sequence of parameterized strokes, which can be rendered into a painting that resembles the input image. Recently, Neural Painting methods that utilize deep learning and reinforcement learning models to predict the stroke sequences have been developed, but suffer from longer infer...

SVG (Scalable Vector Graphics) is a widely used graphics format that possesses excellent scalability and editability. Image vectorization, which aims to convert raster images to SVGs, is an important yet challenging problem in computer vision and graphics. Existing image vectorization methods either suffer from low reconstruction accuracy for compl...

This chapter addresses generating artistic portrait drawings (APDrawings) from images, and we focus on two methods based on generative adversarial networks (GANs). We first introduce the genre of portrait line drawings, and review some existing methods for generating them from images. We also describe the Artistic Portrait Drawing (APDrawing) datas...

Image quality assessment (IQA) and its computational models play a vital role in modern computer vision applications. Research has traditionally focused on signal distortions arising during image compression and transmission, and their impact on perceived image quality. However, little attention is paid to image manipulation that alters an image us...

Universal domain adaptation aims to transfer the knowledge of common classes from the source domain to the target domain without any prior knowledge on the label set, which requires distinguishing in the target domain the unknown samples from the known ones. Recent methods usually focused on categorizing a target sample into one of the source class...

While 3D visual saliency aims to predict regional importance of 3D surfaces in agreement with human visual perception and has been well researched in computer vision and graphics, latest work with eye-tracking experiments shows that state-of-the-art 3D visual saliency methods remain poor at predicting human fixations. Cues emerging prominently from...

Semi-supervised learning has been well developed to help reduce the cost of manual labelling by exploiting a large quantity of unlabelled data. Especially in the application of land cover classification, pixel-level manual labelling in large-scale imagery is labour-intensive and expensive. However, the existing semi-supervised learning methods pay...

Image aesthetics assessment (IAA) is a challenging task due to its highly subjective nature. Most of the current studies rely on large-scale datasets (e.g., AVA and AADB) to learn a general model for all kinds of photography images. However, little light has been shed on measuring the aesthetic quality of artistic images, and the existing datasets...

Land cover mapping provides spatial information on the physical properties of the Earth’s surface for various classes of wetlands, artificial surface and constructions, vineyards, water bodies, etc. Having reliable information on land cover is crucial to developing solutions to a variety of environmental problems, such as the destruction of importa...

Land cover mapping provides spatial information on the physical properties of the Earth’s surface, for various classes of wetlands, artificial surface and constructions, vineyards, water bodies, etc. Having reliable information on land cover is crucial to developing solutions to a variety of environmental problems such as destruction of important w...

Image colorization is a classic and important topic in computer graphics, where the aim is to add color to a monochromatic input image to produce a colorful result. In this survey, we present the history of colorization research in chronological order and summarize popular algorithms in this field. Early works on colorization mostly focused on deve...

Semantic segmentation has been proposed as a tool to accelerate the processing of natural history collection images. However, developing a flexible and resilient segmentation network requires an approach for adaptation which allows processing different datasets with minimal training and validation. This paper presents a cross-validation approach de...

Recently, there has been an upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer (NST). However, the state of performance evaluation in this field is poor, especially compared to the norms in the computer vision and machine learning communitie...

This paper focuses on indoor semantic segmentation based on RGB-D images. Semantic segmentation is a pixel-level classification task that has made steady progress based on fully convolutional networks (FCNs). However, we find there is still room for improvements in the following three aspects. The first is related to multi-scale feature extraction....

Existing methods can generate a high dynamic range (HDR) image from a single low dynamic range (LDR) image using convolutional neural networks (CNNs). However, they are too cumbersome to run on mobile devices with limited computational resources. In this work, we design a lightweight CNN, namely LiTMNet which takes a single LDR image as input and r...

Face portrait line drawing is a unique style of art which is highly abstract and expressive. However, due to its high semantic constraints, many existing methods learn to generate portrait drawings using paired training data, which is costly and time-consuming to obtain. In this paper, we propose a novel method to automatically transform face photo...

Face portrait line drawing is a unique style of art which is highly abstract and expressive. However, due to its high semantic constraints, many existing methods learn to generate portrait drawings using paired training data. In this paper, we propose a novel method to automatically transform face photos to portrait drawings using unpaired training...

With the rapid development of virtual reality (VR) technology, VR headsets, a.k.a. Head-Mounted Displays (HMDs), are widely available, allowing immersive 3D content to be viewed. A natural need for truly immersive VR is to allow bidirectional communication: the user should be able to interact with the virtual world using facial expressions and eye...

This special section of Computers & Graphics (C&G), features the full papers presented at the 14th Eurographics Workshop on 3D Object Retrieval – 3DOR 2021 (https://3dor2021.github.io/). Due to the pandemic, and for the second year in a row, 3DOR was convened online, and this year was hosted by Cardiff University on September 2–3, 2021. Virtual att...

Human voice is an ideal data source for identifying people in many applications. Because of the increasing need for security in different public places, voice biometrics may be a good solution, as we can easily take voice records. This chapter provides a brief overview of the approaches utilized in recognizing speakers, and then presents a novel ap...

This paper presents the results of SHREC’21 track: Quantifying Shape Complexity. Our goal is to investigate how good the submitted shape complexity measures are (i.e. with respect to ground truth) and investigate the relationships between these complexity measures (i.e. with respect to correlations). The dataset consists of three collections: 1800...

Recent facial image synthesis methods have been mainly based on conditional generative models. Sketch-based conditions can effectively describe the geometry of faces, including the contours of facial components, hair structures, as well as salient edges (e.g., wrinkles) on face surfaces but lack effective control of appearance, which is influenced...

Infrared imaging theory is an important theoretical basis for the design of infrared imaging systems, but there is no research on infrared imaging theory for designing thermal microscope imaging systems. Therefore, we studied the performance evaluation and optimization theory of thermal microscope imaging systems. In this paper, we analyzed the dif...

Many attempts have been made to hide information in images, where one main challenge is how to increase the payload capacity without the container image being detected as containing a message. In this paper, we propose a large-capacity Invertible Steganography Network (ISN) for image steganography. We take steganography and the recovery of hidden i...

Recent facial image synthesis methods have been mainly based on conditional generative models. Sketch-based conditions can effectively describe the geometry of faces, including the contours of facial components, hair structures, as well as salient edges (e.g., wrinkles) on face surfaces but lack effective control of appearance, which is influenced...

In this paper, a novel triplet network is proposed for face sketch recognition. A spatial pyramid pooling layer is introduced into the network to deal with different sizes of images, and an attention model on the image space is proposed to extract features from the same location in the photo and sketch. Our attention mechanism builds and improves r...

Estimating correspondence between two shapes continues to be a challenging problem in geometry processing. Most current methods assume deformation to be near-isometric, however this is often not the case. For this paper, a collection of shapes of different animals has been curated, where parts of the animals (e.g., mouths, tails & ears) correspond...

The association between alcohol outlets and violence has long been recognised, and is commonly used to inform policing and licensing policies (such as staggered closing times and zoning). Less investigated, however, is the association between violent crime and other urban points of interest, which while associated with the city centre alcohol consu...

Despite the recent upsurge of activity in image-based non-photorealistic rendering (NPR), and in particular portrait image stylisation, due to the advent of neural style transfer, the state of performance evaluation in this field is limited, especially compared to the norms in the computer vision and machine learning communities. Unfortunately, the...

Humans have the ability to perceive kinetic depth effects, i.e., to perceived 3D shapes from 2D projections of rotating 3D objects. This process is based on a variety of visual cues such as lighting and shading effects. However, when such cues are weak or missing, perception can become faulty, as demonstrated by the famous silhouette illusion examp...

This paper describes a simple image-based method that applies engraving stylisation to portraits using ordered dithering. Face detection is used to estimate a rough proxy geometry of the head consisting of a cylinder, which is used to warp the dither matrix, causing the engraving lines to curve around the face for better stylisation. Finally, an ap...

3D models are commonly used in computer vision and graphics. With the wider availability of mesh data, an efficient and intrinsic deep learning approach to processing 3D meshes is in great need. Unlike images, 3D meshes have irregular connectivity, requiring careful design to capture relations in the data. To utilize the topology information while...

Proteins are natural modular objects usually composed of several domains, each domain bearing a specific function that is mediated through its surface, which is accessible to vicinal molecules. This draws attention to an understudied characteristic of protein structures: surface, that is mostly unexploited by protein structure comparison methods. I...

This paper presents an automatic image synthesis method to transfer the style of an example image to a content image. When standard neural style transfer approaches are used, the textures and colours in different semantic regions of the style image are often applied inappropriately to the content image, ignoring its semantic layout, and ruining the...

This paper develops a novel adaptive gradient-based block compressive sensing (AGbBCS_SP) methodology for noisy image compression and reconstruction. The AGbBCS_SP approach splits an image into blocks by maximizing their sparsity, and reconstructs images by solving a convex optimization problem. In block compressive sensing, the commonly used squar...

Despite significant effort and notable success of neural style transfer, it remains challenging for highly abstract styles, in particular line drawings. In this paper, we propose APDrawingGAN++, a generative adversarial network (GAN) for transforming portrait photos to artistic portrait drawings (APDrawings), which addresses substantial challenges...

Digitisation of natural history collections has evolved from creating databases for the recording of specimens’ catalogue and label data to include digital images of specimens. This has been driven by several important factors, such as a need to increase global accessibility to specimens and to preserve the original specimens by limiting their manu...

Mesh color edit propagation aims to propagate the color from a few color strokes to the whole mesh, which is useful for mesh colorization, color enhancement and color editing, etc. Compared with image edit propagation, luminance information is not available for 3D mesh data, so the color edit propagation is more difficult on 3D meshes than images,...

In order to improve the spatial resolution of an optical micro-scanning thermal microscope system, the micro-scanning position must be accurately calibrated. An adaptive calibration method based on image registration and plane coordinate system is proposed. The meaning of calibration is given, and the principle and method of point calibration are i...

3D models of humans are commonly used within computer graphics and vision, and so the ability to distinguish between body shapes is an important shape retrieval problem. We extend our recent paper which provided a benchmark for testing non-rigid 3D shape retrieval algorithms on 3D human models. This benchmark provided a far stricter challenge than...

Image captioning is the task of generating textual descriptions of images. In order to obtain a better image representation, attention mechanisms have been widely adopted in image captioning. However, in existing models with detection-based attention, the rectangular attention regions are not fine-grained, as they contain irrelevant regions (e.g.,...

This paper develops a novel adaptive gradient-based block compressive sensing (AGbBCS_SP) methodology for noisy image compression and reconstruction. The AGbBCS_SP approach splits an image into blocks by maximizing their sparsity, and reconstructs images by solving a convex optimization problem. The main contribution is to provide an adaptive metho...

This textbook is designed for postgraduate studies in the field of 3D Computer Vision. It also provides a useful reference for industrial practitioners; for example, in the areas of 3D data capture, computer-aided geometric modelling and industrial quality assurance. This second edition is a significant upgrade of existing topics with novel finding...

Sketching is a natural and intuitive communication tool used for expressing concepts or ideas which are difficult to communicate through text or speech alone. Sketching is therefore used for a variety of purposes, from the expression of ideas on two-dimensional (2D) physical media, to object creation, manipulation, or deformation in three-dimension...

3D models are commonly used in computer vision and graphics. With the wider availability of mesh data, an efficient and intrinsic deep learning approach to processing 3D meshes is in great need. Unlike images, 3D meshes have irregular connectivity, requiring careful design to capture relations in the data. To utilize the topology information while...