Search

This paper presents LiteVLoc, a hierarchical visual localization framework that uses a lightweight topo-metric map to represent the environment. The method consists of three sequential modules that estimate camera poses in a coarse-to-fine manner. Unlike mainstream approaches relying on detailed 3D representations, LiteVLoc reduces storage overhead by leveraging learning-based feature matching and geometric solvers for metric pose estimation. A novel dataset for the map-free relocalization task is also introduced. Extensive experiments including localization and navigation in both simulated and real-world scenarios have validate the system's performance and demonstrated its precision and efficiency for large-scale deployment. Code and data will be made publicly available., Comment: 9 pages, 4 figures

We leverage 3D Gaussian Splatting (3DGS) as a scene representation and propose a novel test-time camera pose refinement framework, GSLoc. This framework enhances the localization accuracy of state-of-the-art absolute pose regression and scene coordinate regression methods. The 3DGS model renders high-quality synthetic images and depth maps to facilitate the establishment of 2D-3D correspondences. GSLoc obviates the need for training feature extractors or descriptors by operating directly on RGB images, utilizing the 3D foundation model, MASt3R, for precise 2D matching. To improve the robustness of our model in challenging outdoor environments, we incorporate an exposure-adaptive module within the 3DGS framework. Consequently, GSLoc enables efficient one-shot pose refinement given a single RGB query and a coarse initial pose estimation. Our proposed approach surpasses leading NeRF-based optimization methods in both accuracy and runtime across indoor and outdoor visual localization benchmarks, achieving new state-of-the-art accuracy on two indoor datasets., Comment: Fixed a small bug in the first version and achieved new state-of-the-art accuracy. The project page is available at https://gsloc.active.vision

State-of-the-art hierarchical localisation pipelines (HLoc) employ image retrieval (IR) to establish 2D-3D correspondences by selecting the top-$k$ most similar images from a reference database. While increasing $k$ improves localisation robustness, it also linearly increases computational cost and runtime, creating a significant bottleneck. This paper investigates the relationship between global and local descriptors, showing that greater similarity between the global descriptors of query and database images increases the proportion of feature matches. Low similarity queries significantly benefit from increasing $k$, while high similarity queries rapidly experience diminishing returns. Building on these observations, we propose an adaptive strategy that adjusts $k$ based on the similarity between the query's global descriptor and those in the database, effectively mitigating the feature-matching bottleneck. Our approach optimizes processing time without sacrificing accuracy. Experiments on three indoor and outdoor datasets show that AIR-HLoc reduces feature matching time by up to 30\%, while preserving state-of-the-art accuracy. The results demonstrate that AIR-HLoc facilitates a latency-sensitive localisation system.

Absolute Pose Regressors (APRs) directly estimate camera poses from monocular images, but their accuracy is unstable for different queries. Uncertainty-aware APRs provide uncertainty information on the estimated pose, alleviating the impact of these unreliable predictions. However, existing uncertainty modelling techniques are often coupled with a specific APR architecture, resulting in suboptimal performance compared to state-of-the-art (SOTA) APR methods. This work introduces a novel APR-agnostic framework, HR-APR, that formulates uncertainty estimation as cosine similarity estimation between the query and database features. It does not rely on or affect APR network architecture, which is flexible and computationally efficient. In addition, we take advantage of the uncertainty for pose refinement to enhance the performance of APR. The extensive experiments demonstrate the effectiveness of our framework, reducing 27.4\% and 15.2\% of computational overhead on the 7Scenes and Cambridge Landmarks datasets while maintaining the SOTA accuracy in single-image APRs., Comment: Accepted in in 2024 IEEE International Conference on Robotics and Automation (ICRA). Code: https://github.com/lck666666/HR-APR

Recent years have seen significant improvement in absolute camera pose estimation, paving the way for pervasive markerless Augmented Reality (AR). However, accurate absolute pose estimation techniques are computation- and storage-heavy, requiring computation offloading. As such, AR systems rely on visual-inertial odometry (VIO) to track the device's relative pose between requests to the server. However, VIO suffers from drift, requiring frequent absolute repositioning. This paper introduces MobileARLoc, a new framework for on-device large-scale markerless mobile AR that combines an absolute pose regressor (APR) with a local VIO tracking system. Absolute pose regressors (APRs) provide fast on-device pose estimation at the cost of reduced accuracy. To address APR accuracy and reduce VIO drift, MobileARLoc creates a feedback loop where VIO pose estimations refine the APR predictions. The VIO system identifies reliable predictions of APR, which are then used to compensate for the VIO drift. We comprehensively evaluate MobileARLoc through dataset simulations. MobileARLoc halves the error compared to the underlying APR and achieve fast (80\,ms) on-device inference speed., Comment: Accepted for publication at the 3rd edition of the Pervasive and Resource-Constrained AI (PerConAI) workshop (co-located with PerCom 2024). This article supersedes arXiv:2308.05394

Portable 360$^\circ$ cameras are becoming a cheap and efficient tool to establish large visual databases. By capturing omnidirectional views of a scene, these cameras could expedite building environment models that are essential for visual localization. However, such an advantage is often overlooked due to the lack of valuable datasets. This paper introduces a new benchmark dataset, 360Loc, composed of 360$^\circ$ images with ground truth poses for visual localization. We present a practical implementation of 360$^\circ$ mapping combining 360$^\circ$ images with lidar data to generate the ground truth 6DoF poses. 360Loc is the first dataset and benchmark that explores the challenge of cross-device visual positioning, involving 360$^\circ$ reference frames, and query frames from pinhole, ultra-wide FoV fisheye, and 360$^\circ$ cameras. We propose a virtual camera approach to generate lower-FoV query frames from 360$^\circ$ images, which ensures a fair comparison of performance among different query types in visual localization tasks. We also extend this virtual camera approach to feature matching-based and pose regression-based methods to alleviate the performance loss caused by the cross-device domain gap, and evaluate its effectiveness against state-of-the-art baselines. We demonstrate that omnidirectional visual localization is more robust in challenging large-scale scenes with symmetries and repetitive structures. These results provide new insights into 360-camera mapping and omnidirectional visual localization with cross-device queries., Comment: CVPR 2024. Project Page: https://huajianup.github.io/research/360Loc/

We present VR PreM+, an innovative VR system designed to enhance web exploration beyond traditional computer screens. Unlike static 2D displays, VR PreM+ leverages 3D environments to create an immersive pre-learning experience. Using keyword-based information retrieval allows users to manage and connect various content sources in a dynamic 3D space, improving communication and data comparison. We conducted preliminary and user studies that demonstrated efficient information retrieval, increased user engagement, and a greater sense of presence. These findings yielded three design guidelines for future VR information systems: display, interaction, and user-centric design. VR PreM+ bridges the gap between traditional web browsing and immersive VR, offering an interactive and comprehensive approach to information acquisition. It holds promise for research, education, and beyond., Comment: Accepted for publication at The Eleventh International Symposium of Chinese CHI (Chinese CHI 2023), Bali

This paper presents "AI Nushu," an emerging language system inspired by Nushu (women's scripts), the unique language created and used exclusively by ancient Chinese women who were thought to be illiterate under a patriarchal society. In this interactive installation, two artificial intelligence (AI) agents are trained in the Chinese dictionary and the Nushu corpus. By continually observing their environment and communicating, these agents collaborate towards creating a standard writing system to encode Chinese. It offers an artistic interpretation of the creation of a non-western script from a computational linguistics perspective, integrating AI technology with Chinese cultural heritage and a feminist viewpoint., Comment: Accepted for publication at SIGGRAPH Asia 2023

Markerless Mobile Augmented Reality (AR) aims to anchor digital content in the physical world without using specific 2D or 3D objects. Absolute Pose Regressors (APR) are end-to-end machine learning solutions that infer the device's pose from a single monocular image. Thanks to their low computation cost, they can be directly executed on the constrained hardware of mobile AR devices. However, APR methods tend to yield significant inaccuracies for input images that are too distant from the training set. This paper introduces KS-APR, a pipeline that assesses the reliability of an estimated pose with minimal overhead by combining the inference results of the APR and the prior images in the training set. Mobile AR systems tend to rely upon visual-inertial odometry to track the relative pose of the device during the experience. As such, KS-APR favours reliability over frequency, discarding unreliable poses. This pipeline can integrate most existing APR methods to improve accuracy by filtering unreliable images with their pose estimates. We implement the pipeline on three types of APR models on indoor and outdoor datasets. The median error on position and orientation is reduced for all models, and the proportion of large errors is minimized across datasets. Our method enables state-of-the-art APRs such as DFNetdm to outperform single-image and sequential APR methods. These results demonstrate the scalability and effectiveness of KS-APR for visual localization tasks that do not require one-shot decisions.

Visual Inertial Odometry (VIO) is an essential component of modern Augmented Reality (AR) applications. However, VIO only tracks the relative pose of the device, leading to drift over time. Absolute pose estimation methods infer the device's absolute pose, but their accuracy depends on the input quality. This paper introduces VIO-APR, a new framework for markerless mobile AR that combines an absolute pose regressor (APR) with a local VIO tracking system. VIO-APR uses VIO to assess the reliability of the APR and the APR to identify and compensate for VIO drift. This feedback loop results in more accurate positioning and more stable AR experiences. To evaluate VIO-APR, we created a dataset that combines camera images with ARKit's VIO system output for six indoor and outdoor scenes of various scales. Over this dataset, VIO-APR improves the median accuracy of popular APR by up to 36\% in position and 29\% in orientation, increases the percentage of frames in the high ($0.25 m, 2^{\circ}$) accuracy level by up to 112\% and reduces the percentage of frames predicted below the low ($5 m, 10^\circ$) accuracy greatly. We implement VIO-APR into a mobile AR application using Unity to demonstrate its capabilities. VIO-APR results in noticeably more accurate localization and a more stable overall experience.

With the advancement of virtual reality (VR) technology, virtual displays have become integral to how museums, galleries, and other tourist destinations present their collections to the public. However, the current lack of immersion in virtual reality displays limits the user's ability to experience and appreciate its aesthetics. This paper presents a case study of a creative approach taken by a tourist attraction venue in developing a physical network system that allows visitors to enhance VR's aesthetic aspects based on environmental parameters gathered by external sensors. Our system was collaboratively developed through interviews and sessions with twelve stakeholder groups interested in art and exhibitions. This paper demonstrates how our technological advancements in interaction, immersion, and visual attractiveness surpass those of earlier virtual display generations. Through multimodal interaction, we aim to encourage innovation on the Web and create more visually appealing and engaging virtual displays. It is hoped that the greater online art community will gain fresh insight into how people interact with virtual worlds as a result of this work., Comment: Accepted In Proceedings of the ACM Web Conference 2023, April 30-May 4, 2023, Austin, TX, USA. ACM, New York, NY, USA

We share the largest dataset for the Pakistani Twittersphere consisting of over 49 million tweets, collected during one of the most politically active periods in the country. We collect the data after the deposition of the government by a No Confidence Vote in April 2022. This large-scale dataset can be used for several downstream tasks such as political bias, bots detection, trolling behavior, (dis)misinformation, and censorship related to Pakistani Twitter users. In addition, this dataset provides a large collection of tweets in Urdu and Roman Urdu that can be used for optimizing language processing tasks.

There has been a significant expansion in the use of online social networks (OSNs) to support people experiencing mental health issues. This paper studies the role of Instagram influencers who specialize in coaching people with mental health issues. Using a dataset of 97k posts, we characterize such users' linguistic and behavioural features. We explore how these observations impact audience engagement (as measured by likes). We show that the support provided by these accounts varies based on their self-declared professional identities. For instance, Instagram accounts that declare themselves as Authors offer less support than accounts that label themselves as Coach. We show that increasing information support in general communication positively affects user engagement. However, the effect of vocabulary on engagement is not consistent across the Instagram account types. Our findings shed light on this understudied topic and guide how mental health practitioners can improve outreach.

Since 2021, the term "Metaverse" has been the most popular one, garnering a lot of interest. Because of its contained environment and built-in computing and networking capabilities, a modern car makes an intriguing location to host its own little metaverse. Additionally, the travellers don't have much to do to pass the time while traveling, making them ideal customers for immersive services. Vetaverse (Vehicular-Metaverse), which we define as the future continuum between vehicular industries and Metaverse, is envisioned as a blended immersive realm that scales up to cities and countries, as digital twins of the intelligent Transportation Systems, referred to as "TS-Metaverse", as well as customized XR services inside each Individual Vehicle, referred to as "IV-Metaverse". The two subcategories serve fundamentally different purposes, namely long-term interconnection, maintenance, monitoring, and management on scale for large transportation systems (TS), and personalized, private, and immersive infotainment services (IV). By outlining the framework of Vetaverse and examining important enabler technologies, we reveal this impending trend. Additionally, we examine unresolved issues and potential routes for future study while highlighting some intriguing Vetaverse services., Comment: 27 pages, 19 figures

Human habitation across multiple planets requires communication and social connection between planets. When the infrastructure of a deep space network becomes mature, immersive cyberspace, known as the Metaverse, can exchange diversified user data and host multitudinous virtual worlds. Nevertheless, such immersive cyberspace unavoidably encounters latency in minutes, and thus operates in a turn-taking manner. This Blue Sky paper illustrates a vision of an interplanetary Metaverse that connects Earthian and Martian users in a turn-based Metaverse. Accordingly, we briefly discuss several grand challenges to catalyze research initiatives for the `Digital Big Bang' on Mars., Comment: Accepted Paper in ACM ICMI 2022 (Blue Sky Track)

User Interaction for NFTs (Non-fungible Tokens) is gaining increasing attention. Although NFTs have been traditionally single-use and monolithic, recent applications aim to connect multimodal interaction with human behaviour. This paper reviews the related technological approaches and business practices in NFT art. We highlight that multimodal interaction is a currently under-studied issue in mainstream NFT art, and conjecture that multimodal interaction is a crucial enabler for decentralization in the NFT community. We propose a framework that combines a bottom-up approach with AI multimodal process. Through this framework, we put forward integrating human behaviour data into generative NFT units, as "multimodal interactive NFT". Our work displays the possibilities of NFTs in the art world, beyond the traditional 2D and 3D static content., Comment: 7 pages, 5 figures

The Metaverse refers to a virtual-physical blended space in which multiple users can concurrently interact with a unified computer-generated environment and other users, which can be regarded as the next significant milestone of the current cyberspace. This article primarily discusses the development and challenges of the Metaverse. We first briefly describe the development of cyberspace and the necessity of technology enablers. Accordingly, our bottom-up approach highlights three critical technology enablers for the Metaverse: networks, systems, and users. Also, we highlight a number of indispensable issues, under technological and ecosystem perspectives, that build and sustain the Metaverse., Comment: 7 pages, 2 figures

During the COVID-19 pandemic, most countries have experienced some form of remote education through video conferencing software platforms. However, these software platforms fail to reduce immersion and replicate the classroom experience. The currently emerging Metaverse addresses many of such limitations by offering blended physical-digital environments. This paper aims to assess how the Metaverse can support and improve e-learning. We first survey the latest applications of blended environments in education and highlight the primary challenges and opportunities. Accordingly, we derive our proposal for a virtual-physical blended classroom configuration that brings students and teachers into a shared educational Metaverse. We focus on the system architecture of the Metaverse classroom to achieve real-time synchronization of a large number of participants and activities across physical (mixed reality classrooms) and virtual (remote VR platform) learning spaces. Our proposal attempts to transform the traditional physical classroom into virtual-physical cyberspace as a new social network of learners and educators connected at an unprecedented scale., Comment: 6 pages, 3 figures, accepted in 2022 IEEE 42nd ICDCS Workshop on SocialMeta

Online Social Networks (OSNs) play a significant role in information sharing during a crisis. The data collected during such a crisis can reflect the large scale public opinions and sentiment. In addition, OSN data can also be used to study different campaigns that are employed by various entities to engineer public opinions. Such information sharing campaigns can range from spreading factual information to propaganda and misinformation. We provide a Twitter dataset of the 2022 Russo-Ukrainian conflict. In the first release, we share over 1.6 million tweets shared during the 1st week of the crisis.

Recent advances in extended reality (XR) technologies have enabled new and increasingly realistic empathy tools and experiences. In XR, all interactions take place in different spatial contexts, all with different features, affordances, and constraints. We present a systematic literature survey of recent work on empathy in XR. As a result, we contribute a research roadmap with three future opportunities in XR-enabled empathy research across both physical and virtual spaces.

Mobile cloud gaming enables high-end games on constrained devices by streaming the game content from powerful servers through mobile networks. Mobile networks suffer from highly variable bandwidth, latency, and losses that affect the gaming experience. This paper introduces Nebula, an end-to-end cloud gaming framework to minimize the impact of network conditions on the user experience. Nebula relies on an end-to-end distortion model adapting the video source rate and the amount of frame-level redundancy based on the measured network conditions. As a result, it minimizes the motion-to-photon (MTP) latency while protecting the frames from losses. We fully implement Nebula and evaluate its performance against the state of the art techniques and latest research in real-time mobile cloud gaming transmission on a physical testbed over emulated and real wireless networks. Nebula consistently balances MTP latency (<140 ms) and visual quality (>31 dB) even in highly variable environments. A user experiment confirms that Nebula maximizes the user experience with high perceived video quality, playability, and low user load., Comment: 12, 13, accepted in conference: TheWebConf'22, uses subfig.dtx

Driven by the recent improvements in device and networks capabilities, Extended Reality (XR) is becoming more pervasive; industry and academia alike envision ambitious projects such as the metaverse. However, XR is still limited by the current architecture of mobile systems. This paper makes the case for an XR-specific operating system (XROS). Such an XROS integrates hardware-support, computer vision algorithms, and XR-specific networking as the primitives supporting XR technology. These primitives represent the physical-digital world as a single shared resource among applications. Such an XROS allows for the development of coherent and system-wide interaction and display methods, systematic privacy preservation on sensor data, and performance improvement while simplifying application development., Comment: 6 pages, 4 figures