Deep Learning for Visual Computing

Abstract Photographs are characterized by different compositional attributes like the Rule of Thirds, depth of field, vanishing-lines etc. The presence or absence of one or more of these attributes contributes ...

Abstract Limited angular resolution is one of the main obstacles for practical applications of light fields. Although numerous approaches have been proposed to enhance angular resolution, view selection strategies have ...

Spatial-temporal, channel-wise, and motion patterns are three complementary and crucial types of information for video action recognition. Conventional 2D CNNs are computationally cheap but cannot catch temporal relationships; 3D CNNs ...

Abstract Aesthetic image captioning (AIC) refers to the multi-modal task of generating critical textual feedbacks for photographs. While in natural image captioning (NIC), deep models are trained in an end-to-end ...

Abstract We present the first generative adversarial network (GAN) for natural image matting. Our novel generator network is trained to predict visually appealing alphas with the addition of the adversarial ...

Abstract We present a method for augmenting hand-drawn characters and creatures with global illumination effects. Given a single view drawing only, we use a novel CNN to predict a high-quality ...

Abstract Egocentric gestures are the most natural form of communication for humans to interact with wearable devices such as VR/AR helmets and glasses. A major issue in such scenarios for ...

This webpage is dedicated to the publications about color mismatch correction in stereoscopic 3D (S3D) images and videos. Here, you can find the publications and the related publicly available material ...

This page contains related materials for learning-based colorfulness estimation. ABSTRACT Measuring the colorfulness of a natural or virtual scene is critical for many applications in image processing field ranging from ...

Abstract In this paper we present a convolutional neural network (CNN) to predict multiple lens distortion parameters from a single input image. Unlike other methods, our network is suitable to ...

Proposed by Richard BlythmanEmail: blythmar(at)tcd.ie Tele-health is fast becoming more popular and physiotherapy sessions are often undertaken during live video streaming sessions. Smart video analysis using deep learning models (such ...

In this paper we present a new fully automatic pipeline for generating shading effects on hand-drawn characters. Our method takes as input a single digitized sketch of any resolution and ...

Abstract A computationally fast tone mapping operator (TMO) that can quickly adapt to a wide spectrum of high dynamic range (HDR) content is quintessential for visualization on varied low dynamic ...

In this paper, we introduce a novel interactive depth map creation approach for image sequences which uses depth scribbles as input at user-defined keyframes. These scribbled depth values are then ...

Please click the image or here DublinCity Dataset to access the dataset! ...

Natural interaction with virtual objects in AR/VR environments makes for a smooth user experience. Gestures are a natural extension from real world to augmented space to achieve these interactions. Finding ...

Abstract In natural image matting, the goal is to estimate the opacity of the foreground object in the image. This opacity controls the way the foreground and background is blended ...

Abstract We address the problem of exposure correction of dark, blurry and noisy images captured in low-light conditions in the wild. Classical image-denoising filters work well in the frequency space ...

Abstract Style transfer involves combining the style of one image with the content of another to form a new image. Unlike traditional two-dimensional images which only capture the spatial intensity ...

As part of our paper Augmenting Hand-Drawn Art with Global Illumination Effects through Surface Inflation, we release a high-resolution LineArt dataset of line drawings with corresponding ground-truth normal and depth ...

Abstract The prediction of Visual Attention data from any kind of media is of valuable use to content creators and used to efficiently drive encoding algorithms. With the current trend ...

Abstract High angular resolution is advantageous for practical applications of light fields. In order to enhance the angular resolution of light fields, view synthesis methods can be utilized to generate ...

Ego hand gestures can be used as an interface in AR and VR environments. While the context of an image is important for tasks like scene understanding, object recognition, image ...

Abstract The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer algorithms can apply ...

Abstract An omnidirectional image (ODI) enables viewers to look in every direction from a fixed point through a headmounted display providing an immersive experience compared to that of a standard ...

Abstract Omnidirectional videos (ODVs) with spatial audio enable viewers to perceive 360° directions of audio and visual signals during the consumption of ODVs with head-mounted displays (HMDs). By predicting salient ...

Abstract Ambisonics i.e., a full-sphere surround sound, is quintessential with 360-degree visual content to provide a realistic virtual reality (VR) experience. While 360-degree visual content capture gained a tremendous boost ...

Fig. 1: Illustration of viewport prediction in 360° video. Our model aims to predict the viewport scanpath in the forthcoming F seconds given the past H-second viewport scanpath. Abstract Virtual ...

Proposed by Richard BlythmanEmail: blythmar(at)tcd.ie Motion capture systems are often used to capture ground truth 3D pose labels in combination with RGB videos for training deep computer vision models for ...

Creative studios tend to produce an overwhelming amount of content everyday and being able to manage these data and reuse it in new productions represent a way for reducing costs ...