Goto

Collaborating Authors

Results


Pushing Buttons: Get lost in Elden Ring's maddening, engaging world

The Guardian

Welcome to Pushing Buttons, the Guardian's gaming newsletter. If you'd like to receive it in your inbox every week, just pop your email in below – and check your inbox (and spam) for the confirmation email. Like a lot of people interested in video games, I have spent most of the past week rampaging across the Lands Between on a phantom horse, slaying trolls, exploring castles and being repeatedly stamped on by giant boss monsters. The critical consensus is that Elden Ring, a new open-world fantasy adventure from the makers of the Dark Souls series, might just be one of the greatest games ever made. It is extraordinarily beautiful to look at, it's incredibly challenging and it encourages players to discover its secrets however they see fit.


Pose Estimation of Specific Rigid Objects

arXiv.org Artificial Intelligence

In this thesis, we address the problem of estimating the 6D pose of rigid objects from a single RGB or RGB-D input image, assuming that 3D models of the objects are available. This problem is of great importance to many application fields such as robotic manipulation, augmented reality, and autonomous driving. First, we propose EPOS, a method for 6D object pose estimation from an RGB image. The key idea is to represent an object by compact surface fragments and predict the probability distribution of corresponding fragments at each pixel of the input image by a neural network. Each pixel is linked with a data-dependent number of fragments, which allows systematic handling of symmetries, and the 6D poses are estimated from the links by a RANSAC-based fitting method. EPOS outperformed all RGB and most RGB-D and D methods on several standard datasets. Second, we present HashMatch, an RGB-D method that slides a window over the input image and searches for a match against templates, which are pre-generated by rendering 3D object models in different orientations. The method applies a cascade of evaluation stages to each window location, which avoids exhaustive matching against all templates. Third, we propose ObjectSynth, an approach to synthesize photorealistic images of 3D object models for training methods based on neural networks. The images yield substantial improvements compared to commonly used images of objects rendered on top of random photographs. Fourth, we introduce T-LESS, the first dataset for 6D object pose estimation that includes 3D models and RGB-D images of industry-relevant objects. Fifth, we define BOP, a benchmark that captures the status quo in the field. BOP comprises eleven datasets in a unified format, an evaluation methodology, an online evaluation system, and public challenges held at international workshops organized at the ICCV and ECCV conferences.


When Creators Meet the Metaverse: A Survey on Computational Arts

arXiv.org Artificial Intelligence

The metaverse, enormous virtual-physical cyberspace, has brought unprecedented opportunities for artists to blend every corner of our physical surroundings with digital creativity. This article conducts a comprehensive survey on computational arts, in which seven critical topics are relevant to the metaverse, describing novel artworks in blended virtual-physical realities. The topics first cover the building elements for the metaverse, e.g., virtual scenes and characters, auditory, textual elements. Next, several remarkable types of novel creations in the expanded horizons of metaverse cyberspace have been reflected, such as immersive arts, robotic arts, and other user-centric approaches fuelling contemporary creative outputs. Finally, we propose several research agendas: democratising computational arts, digital privacy, and safety for metaverse artists, ownership recognition for digital artworks, technological challenges, and so on. The survey also serves as introductory material for artists and metaverse technologists to begin creations in the realm of surrealistic cyberspace.


TMBuD: A dataset for urban scene building detection

arXiv.org Artificial Intelligence

Computer Vision (CV) aims to create computational models that can mimic the human visual system. From an engineering point of view, CV aims to build autonomous systems which could perform some of the tasks that the human visual system is able to accomplish [1]. Urban scenarios reconstruction and understanding of it is an area of research with several applications nowadays: entertainment industry, computer gaming, movie making, digital mapping for mobile devices, digital mapping for car navigation, urban planning, driving. Understanding urban scenarios has become much more important with the evolution of Augmented Reality (AR). AR is successfully exploited in many domains nowadays, one of them being culture and tourism, an area in which the authors of this paper carried multiple research projects [2], [3], [4].


5G & The Future Of Connectivity

#artificialintelligence

The next generation of wireless technology could affect a wide range of industries, from healthcare to financial services to retail. The technology enables faster data transfer speeds -- up to 10x faster than the speeds achievable with older standards -- lower latency, and greater network capacity. As a result, 5G creates a tremendous opportunity for numerous industries, but also sets the stage for large-scale disruption. Download the free report to understand what 5G is, the industries it's disrupting, and the drivers paving the way for its implementation. As of June 2021, commercial 5G services have already been deployed across more than 1,500 cities in 60 countries worldwide, according to Viavi Solutions. The number of IoT devices -- which will rely on 5G to transmit vast amounts of data in real time -- is projected to grow from 12B in 2020 to 30B in 2025, per IoT Analytics, more than 4 devices for every person on Earth. Executives across industries are already jostling to take advantage of 5G tech -- and avoid being disrupted by it. Earnings call mentions of 5G have soared in recent years. From enabling remote robotic surgery and autonomous cars to improving crop management, 5G is poised to transform many of the world's biggest industries. The impact of 5G on manufacturing could be huge. It's estimated that improved connectivity through 5G will create $13T in global economic value across industries by 2035, according to IHS Markit. A third of that total is projected to come from the manufacturing sector alone. This would enable manufacturers to build "smart factories" that rely on automation, augmented reality, and IoT. And with 5G powering large amounts of IoT devices and sensors around the factory, artificial intelligence can be integrated more deeply with operations. On fast-paced assembly lines, even microseconds of latency can cause costly disruptions for the manufacturer.


How Artificial Intelligence Is Changing Media & Communications

#artificialintelligence

New media can be defined as a highly interactive digital technology which allows people to interact anywhere anytime. This has evolved as a non-tangible channel for communication on the preset of growth in Information Technology. The ability to transform content to a digitized format allowed new-age media to take shape within the internet. Accessibility through hand-held devices like mobile platforms, personal computers, digital devices, and virtual computing machines has aided the growth of new-age media. The medium of new media is not just restricted to social networking platforms, blogs, online newspapers, digital games and virtual reality, but any aspect of communication that can be communicated real-time, processed, stored and delivered in formats of data instantaneously.


AI in (and for) Games

arXiv.org Artificial Intelligence

This chapter outlines the relation between artificial intelligence (AI) / machine learning (ML) algorithms and digital games. This relation is two-fold: on one hand, AI/ML researchers can generate large, in-the-wild datasets of human affective activity, player behaviour (i.e. actions within the game world), commercial behaviour, interaction with graphical user interface elements or messaging with other players, while games can utilise intelligent algorithms to automate testing of game levels, generate content, develop intelligent and responsive non-player characters (NPCs) or predict and respond player behaviour across a wide variety of player cultures. In this work, we discuss some of the most common and widely accepted uses of AI/ML in games and how intelligent systems can benefit from those, elaborating on estimating player experience based on expressivity and performance, and on generating proper and interesting content for a language learning game.


Artificial Intelligence in the Creative Industries: A Review

arXiv.org Artificial Intelligence

This paper reviews the current state of the art in Artificial Intelligence (AI) technologies and applications in the context of the creative industries. A brief background of AI, and specifically Machine Learning (ML) algorithms, is provided including Convolutional Neural Network (CNNs), Generative Adversarial Networks (GANs), Recurrent Neural Networks (RNNs) and Deep Reinforcement Learning (DRL). We categorise creative applications into five groups related to how AI technologies are used: i) content creation, ii) information analysis, iii) content enhancement and post production workflows, iv) information extraction and enhancement, and v) data compression. We critically examine the successes and limitations of this rapidly advancing technology in each of these areas. We further differentiate between the use of AI as a creative tool and its potential as a creator in its own right. We foresee that, in the near future, machine learning-based AI will be adopted widely as a tool or collaborative assistant for creativity. In contrast, we observe that the successes of machine learning in domains with fewer constraints, where AI is the `creator', remain modest. The potential of AI (or its developers) to win awards for its original creations in competition with human creatives is also limited, based on contemporary technologies. We therefore conclude that, in the context of creative industries, maximum benefit from AI will be derived where its focus is human centric -- where it is designed to augment, rather than replace, human creativity.


Raccoons vs Demons: multiclass labeled P300 dataset

arXiv.org Machine Learning

We publish dataset of visual P300 BCI performed in Virtual Reality (VR) game Raccoons versus Demons (RvD). Data contains reach labels incorporating information about stimulus chosen enabling us to estimate model's confidence at each stimulus prediction stage. Data and experiments code are available at https://gitlab.com/impulse-neiry_public/raccoons-vs-demons


Ultra-rare 'Nintendo PlayStation' console sells for $360,000 at auction

Daily Mail - Science & tech

A prototype of the unreleased'Nintendo PlayStation' console has sold for $360,000 (£273,096) at auction – nearly $1 million less than an earlier rejected offer. The super-rare console, which was sold with a Sony-branded SNES controller and cartridge that enables CD-Rom functionality, was sold by Dallas-based auction house Heritage Auctions on Friday. The collectors' item is a rare artefact from a brief collaboration between Japanese gaming giants Sony and Nintendo before they took separate paths in the video game market. The winner bidder was entrepreneur and video game collector Greg McLemore, who beat out other bidders including Palmer Luckey, founder of Facebook's Oculus VR platform. The previous owner of the prototype had reportedly turned down $1.2 million to put it up for auction – meaning he's missed out on nearly $850,000.