Mar Gonzalez-Franco

Junjiao Tian, Lavisha Aggarwal, Andrea Colaco et al.

Producing quality segmentation masks for images is a fundamental problem in computer vision. Recent research has explored large-scale supervised training to enable zero-shot segmentation on virtually any image style and unsupervised training to enable segmentation without dense annotations. However, constructing a model capable of segmenting anything in a zero-shot manner without any annotations is still challenging. In this paper, we propose to utilize the self-attention layers in stable diffusion models to achieve this goal because the pre-trained stable diffusion model has learned inherent concepts of objects within its attention layers. Specifically, we introduce a simple yet effective iterative merging process based on measuring KL divergence among attention maps to merge them into valid segmentation masks. The proposed method does not require any training or language dependency to extract quality segmentation for any images. On COCO-Stuff-27, our method surpasses the prior unsupervised zero-shot SOTA method by an absolute 26% in pixel accuracy and 17% in mean IoU. The project page is at \url{https://sites.google.com/view/diffseg/home}.

Anders Christensen, Nooshin Mojab, Khushman Patel et al.

Spherical or omni-directional images offer an immersive visual format appealing to a wide range of computer vision applications. However, geometric properties of spherical images pose a major challenge for models and metrics designed for ordinary 2D images. Here, we show that direct application of Fréchet Inception Distance (FID) is insufficient for quantifying geometric fidelity in spherical images. We introduce two quantitative metrics accounting for geometric constraints, namely Omnidirectional FID (OmniFID) and Discontinuity Score (DS). OmniFID is an extension of FID tailored to additionally capture field-of-view requirements of the spherical format by leveraging cubemap projections. DS is a kernel-based seam alignment score of continuity across borders of 2D representations of spherical images. In experiments, OmniFID and DS quantify geometry fidelity issues that are undetected by FID.

Mustafa Doga Dogan, Eric J. Gonzalez, Karan Ahuja et al.

Seamless integration of physical objects as interactive digital entities remains a challenge for spatial computing. This paper explores Augmented Object Intelligence (AOI) in the context of XR, an interaction paradigm that aims to blur the lines between digital and physical by equipping real-world objects with the ability to interact as if they were digital, where every object has the potential to serve as a portal to digital functionalities. Our approach utilizes real-time object segmentation and classification, combined with the power of Multimodal Large Language Models (MLLMs), to facilitate these interactions without the need for object pre-registration. We implement the AOI concept in the form of XR-Objects, an open-source prototype system that provides a platform for users to engage with their physical environment in contextually relevant ways using object-based context menus. This system enables analog objects to not only convey information but also to initiate digital actions, such as querying for details or executing tasks. Our contributions are threefold: (1) we define the AOI concept and detail its advantages over traditional AI assistants, (2) detail the XR-Objects system's open-source design and implementation, and (3) show its versatility through various use cases and a user study.

Zhaochong An, Orest Kupyn, Théo Uscidda et al.

Large-scale video diffusion models achieve impressive visual quality, yet often fail to preserve geometric consistency. Prior approaches improve consistency either by augmenting the generator with additional modules or applying geometry-aware alignment. However, architectural modifications can compromise the generalization of internet-scale pretrained models, while existing alignment methods are limited to static scenes and rely on RGB-space rewards that require repeated VAE decoding, incurring substantial compute overhead and failing to generalize to highly dynamic real-world scenes. To preserve the pretrained capacity while improving geometric consistency, we propose VGGRPO (Visual Geometry GRPO), a latent geometry-guided framework for geometry-aware video post-training. VGGRPO introduces a Latent Geometry Model (LGM) that stitches video diffusion latents to geometry foundation models, enabling direct decoding of scene geometry from the latent space. By constructing LGM from a geometry model with 4D reconstruction capability, VGGRPO naturally extends to dynamic scenes, overcoming the static-scene limitations of prior methods. Building on this, we perform latent-space Group Relative Policy Optimization with two complementary rewards: a camera motion smoothness reward that penalizes jittery trajectories, and a geometry reprojection consistency reward that enforces cross-view geometric coherence. Experiments on both static and dynamic benchmarks show that VGGRPO improves camera stability, geometry consistency, and overall quality while eliminating costly VAE decoding, making latent-space geometry-guided reinforcement an efficient and flexible approach to world-consistent video generation.

Xiaoan Liu, DaeHo Lee, Eric J Gonzalez et al.

We present VisionClaw, an always-on wearable AI agent that integrates live egocentric perception with agentic task execution. Running on Meta Ray-Ban smart glasses, VisionClaw continuously perceives real-world context and enables in-situ, speech-driven action initiation and delegation via OpenClaw AI agents. Therefore, users can directly execute tasks through the smart glasses, such as adding real-world objects to an Amazon cart, generating notes from physical documents, receiving meeting briefings on the go, creating events from posters, or controlling IoT devices. We evaluate VisionClaw through a controlled laboratory study (N=12) and a longitudinal deployment study (N=5). Results show that integrating perception and execution enables faster task completion and reduces interaction overhead compared to non-always-on and non-agent baselines. Beyond performance gains, deployment findings reveal a shift in interaction: tasks are initiated opportunistically during ongoing activities, and execution is increasingly delegated rather than manually controlled. These results suggest a new paradigm for wearable AI agents, where perception and action are continuously coupled to support situated, hands-free interaction.

Mathias N. Lystbæk, Haley Adams, Ranjith Kagathi Ananda et al.

Audio-only walking navigation can leave users disoriented, relying on vague cardinal directions and lacking real-time environmental context, leading to frequent errors. To address this, we present a novel system that integrates a Vision Language Model (VLM) with a spatial audio cue. Our system extracts environmental landmarks to anchor navigation instructions and, crucially, provides a directional spatial audio signal when the user faces the wrong direction, indicating the precise turn direction. In a user study (n=12), the spatial audio cue with VLM reduced route deviations compared to both VLM-only and Google Maps (audio-only) baseline systems. Users reported that the spatial audio cue effectively supported orientation and that landmark-anchored instructions provided a better navigation experience over audio-only Google Maps. This work serves as an initial look at the utility of future audio-only navigation systems for incorporating directional cues, especially real-time corrective spatial audio.

Xiaoan Liu, Eric J Gonzalez, Nels Numan et al.

Bridging the physical and digital world through interaction remains a core challenge in augmented reality (AR). Existing systems target single objects, limiting support for planning, comparison, and assembly tasks that depend on relationships among multiple items. We present Semantic Reality, an AR system focused on surfacing inter-object connectivity and making it interactive. Leveraging multimodal reasoning, spatial anchoring, and physical action recognition, Semantic Reality maintains a persistent model of objects around the user and their relationships. Connections are visualized in-situ to highlight compatibility, reveal next steps, and reduce ambiguity during tasks. We contribute a connectivity-centered interaction paradigm and a system architecture that couples anchor tracking, action sensing, and model inference to construct a live connectivity graph. In an exploratory study comparing Semantic Reality to a single-object baseline, participants reported clearer inter-object understanding and higher engagement and satisfaction, without increased workload. A scenario study illustrates where connectivity aids planning, sequencing, and disambiguation.

Jazmin Collins, Prasanthi Gurumurthy, Eric J. Gonzalez et al.

The gaze-and-pinch framework offers a high-fidelity interaction modality for spatial computing in virtual reality (VR), yet it remains vulnerable to coordination errors--timing misalignments between gaze fixation and pinch gestures. These errors are categorized into two types: late triggers (gaze leaves a target before pinch) and early triggers (pinch before gaze arrival on target). While late triggers are well-studied, early triggers lack robust solutions. We investigate two heuristics--STICKY selection (temporal buffer) and MAGNETIC selection (spatial field)--to mitigate these errors. A within-subjects study (N = 9) on the Samsung Galaxy XR evaluated these heuristics against a baseline. Findings indicate that while throughput and selection time remained stable, the heuristics fundamentally shifted user behavior and significantly reduced errors during selection. Notably, MAGNETIC selection induced an "offloading" effect where users traded precision for speed. Additionally, the heuristics reclassified ambiguous failures as explainable coordination errors. We provide recommendations for selection heuristics that enhance interaction speed and cognitive agency in virtual reality.

Vasco Xu, Brian Chen, Eric J. Gonzalez et al.

Mid-air gestures in Extended Reality (XR) often cause fatigue and imprecision. Surface-based interactions offer improved accuracy and comfort, but current egocentric vision methods struggle due to hand tracking challenges and unreliable surface plane estimation. We introduce SurfaceXR, a sensor fusion approach combining headset-based hand tracking with smartwatch IMU data to enable robust inputs on everyday surfaces. Our insight is that these modalities are complementary: hand tracking provides 3D positional data while IMUs capture high-frequency motion. A 21-participant study validates SurfaceXR's effectiveness for touch tracking and 8-class gesture recognition, demonstrating significant improvements over single-modality approaches.

Esen K. Tütüncü, Mar Gonzalez-Franco, Khushman Patel et al.

As Extended Reality (XR) systems increasingly map and understand the physical world, interacting with these blended representations remains challenging. The current push for "natural" inputs has its trade-offs: touch is limited by human reach and fatigue, while gaze often lacks the precision for fine interaction. To bridge this gap, we introduce World Mouse, a cross-reality cursor that reinterprets the familiar 2D desktop mouse for complex 3D scenes. The system is driven by two core mechanisms: within-object interaction, which uses surface normals for precise cursor placement, and between-object navigation, which leverages interpolation to traverse empty space. Unlike previous virtual-only approaches, World Mouse leverages semantic segmentation and mesh reconstruction to treat physical objects as interactive surfaces. Through a series of prototypes, including object manipulation and screen-to-world transitions, we illustrate how cross-reality cursors may enable seamless interactions across real and virtual environments.

Xiao Xiao, Hayoun Noh, Mar Gonzalez-Franco

Conversational AI is increasingly personalized around users' preferences, histories, goals, and knowledge, but much less around how users interpret and take up model outputs to construct and understand their reality. We draw on Robert Kegan's constructive-developmental theory as a complementary lens on this dimension. Existing methods for assessing developmental stage in the Keganian tradition rely either on expert interviews that do not scale or on sentence-completion instruments that are proprietary, lengthy, or invasive. To make this perspective tractable for LLM evaluation, we introduce the Developmental Sentence Completion Test (DSCT), a 20-item instrument designed to elicit developmental signal in self-administered text. Throughout, we treat the resulting labels as characterizations of stage-like structure in elicited responses, not as validated person-level developmental stage. We then ask how much of that signal can be recovered by LLMs across three elicited response regimes: simulated personas, real human respondents, and default model-generated answers. On simulated personas, top frontier models recover simulator-intended labels with high accuracy. On real human DSCT responses, human-LLM agreement is fair, with much stronger within-neighborhood than exact agreement. Finally, when LLMs answer DSCT prompts without persona-conditioning, their responses exhibit stable stage-like differences across model families, with larger and newer models tending to generate higher-rated text. These results suggest that stage-conditioned signal is cleaner in synthetic responses than in human-written DSCT text, and that the core constraint for stage-aware conversational AI is not classifier accuracy alone, but the availability of developmental signal from elicited text.

Ryo Suzuki, Mar Gonzalez-Franco, Misha Sra et al.

This workshop brings together experts and practitioners from augmented reality (AR) and artificial intelligence (AI) to shape the future of AI-in-the-loop everyday AR experiences. With recent advancements in both AR hardware and AI capabilities, we envision that everyday AR -- always-available and seamlessly integrated into users' daily environments -- is becoming increasingly feasible. This workshop will explore how AI can drive such everyday AR experiences. We discuss a range of topics, including adaptive and context-aware AR, generative AR content creation, always-on AI assistants, AI-driven accessible design, and real-world-oriented AI agents. Our goal is to identify the opportunities and challenges in AI-enabled AR, focusing on creating novel AR experiences that seamlessly blend the digital and physical worlds. Through the workshop, we aim to foster collaboration, inspire future research, and build a community to advance the research field of AI-enhanced AR.

Xiaoan Liu, Difan Jia, Xianhao Carton Liu et al.

Interacting with real-world objects in Mixed Reality (MR) often proves difficult when they are crowded, distant, or partially occluded, hindering straightforward selection and manipulation. We observe that these difficulties stem from performing interaction directly on physical objects, where input is tightly coupled to their physical constraints. Our key insight is to decouple interaction from these constraints by introducing proxies-abstract representations of real-world objects. We embody this concept in Reality Proxy, a system that seamlessly shifts interaction targets from physical objects to their proxies during selection. Beyond facilitating basic selection, Reality Proxy uses AI to enrich proxies with semantic attributes and hierarchical spatial relationships of their corresponding physical objects, enabling novel and previously cumbersome interactions in MR - such as skimming, attribute-based filtering, navigating nested groups, and complex multi object selections - all without requiring new gestures or menu systems. We demonstrate Reality Proxy's versatility across diverse scenarios, including office information retrieval, large-scale spatial navigation, and multi-drone control. An expert evaluation suggests the system's utility and usability, suggesting that proxy-based abstractions offer a powerful and generalizable interaction paradigm for future MR systems.

Steven Abreu, Tiffany D. Do, Karan Ahuja et al.

Intelligent assistance involves not only understanding but also action. Existing ego-centric video datasets contain rich annotations of the videos, but not of actions that an intelligent assistant could perform in the moment. To address this gap, we release PARSE-Ego4D, a new set of personal action recommendation annotations for the Ego4D dataset. We take a multi-stage approach to generating and evaluating these annotations. First, we used a prompt-engineered large language model (LLM) to generate context-aware action suggestions and identified over 18,000 action suggestions. While these synthetic action suggestions are valuable, the inherent limitations of LLMs necessitate human evaluation. To ensure high-quality and user-centered recommendations, we conducted a large-scale human annotation study that provides grounding in human preferences for all of PARSE-Ego4D. We analyze the inter-rater agreement and evaluate subjective preferences of participants. Based on our synthetic dataset and complete human annotations, we propose several new tasks for action suggestions based on ego-centric videos. We encourage novel solutions that improve latency and energy requirements. The annotations in PARSE-Ego4D will support researchers and developers who are working on building action recommendation systems for augmented and virtual reality systems.

Momona Yamagami, Sasa Junuzovic, Mar Gonzalez-Franco et al.

Virtual Reality (VR) applications often require users to perform actions with two hands when performing tasks and interacting with objects in virtual environments. Although bimanual interactions in VR can resemble real-world interactions -- thus increasing realism and improving immersion -- they can also pose significant accessibility challenges to people with limited mobility, such as for people who have full use of only one hand. An opportunity exists to create accessible techniques that take advantage of users' abilities, but designers currently lack structured tools to consider alternative approaches. To begin filling this gap, we propose Two-in-One, a design space that facilitates the creation of accessible methods for bimanual interactions in VR from unimanual input. Our design space comprises two dimensions, bimanual interactions and computer assistance, and we provide a detailed examination of issues to consider when creating new unimanual input techniques that map to bimanual interactions in VR. We used our design space to create three interaction techniques that we subsequently implemented for a subset of bimanual interactions and received user feedback through a video elicitation study with 17 people with limited mobility. Our findings explore complex tradeoffs associated with autonomy and agency and highlight the need for additional settings and methods to make VR accessible to people with limited mobility.

Ryo Suzuki, Eyal Ofek, Mike Sinclair et al.

HapticBots introduces a novel encountered-type haptic approach for Virtual Reality (VR) based on multiple tabletop-size shape-changing robots. These robots move on a tabletop and change their height and orientation to haptically render various surfaces and objects on-demand. Compared to previous encountered-type haptic approaches like shape displays or robotic arms, our proposed approach has an advantage in deployability, scalability, and generalizability -- these robots can be easily deployed due to their compact form factor. They can support multiple concurrent touch points in a large area thanks to the distributed nature of the robots. We propose and evaluate a novel set of interactions enabled by these robots which include: 1) rendering haptics for VR objects by providing just-in-time touch-points on the user's hand, 2) simulating continuous surfaces with the concurrent height and position change, and 3) enabling the user to pick up and move VR objects through graspable proxy objects. Finally, we demonstrate HapticBots with various applications, including remote collaboration, education and training, design and 3D modeling, and gaming and entertainment.

Mar Gonzalez-Franco, Julio Cermeron, Katie Li et al.

In the complex manufacturing sector a considerable amount of resources are focused on developing new skills and training workers. In that context, increasing the effectiveness of those processes and reducing the investment required is an outstanding issue. In this paper we present an experiment that shows how modern Human Computer Interaction (HCI) metaphors such as collaborative mixed-reality can be used to transmit procedural knowledge and could eventually replace other forms of face-to-face training. We implement a real-time Immersive Augmented Reality (IAR) setup with see-through cameras that allows for collaborative interactions that can simulate conventional forms of training. The obtained results indicate that people who took the IAR training achieved the same performance than people in the conventional face-to-face training condition. These results, their implications for future training and the use of HCI paradigms in this context are discussed in this paper.

Jacob Thorn, Rodrigo Pizarro, Bernhard Spanlang et al.

Consumer 3D scanners and depth cameras are increasingly being used to generate content and avatars for Virtual Reality (VR) environments and avoid the inconveniences of hand modeling; however, it is sometimes difficult to evaluate quantitatively the mesh quality at which 3D scans should be exported, and whether the object perception might be affected by its shading. We propose using a paired-comparisons test based on psychophysics of perception to do that evaluation. As psychophysics is not subject to opinion, skill level, mental state, or economic situation it can be considered a quantitative way to measure how people perceive the mesh quality. In particular, we propose using the psychophysical measure for the comparison of four different levels of mesh quality (1K, 5K, 10K and 20K triangles). We present two studies within subjects: in one we investigate the quality perception variations of seeing an object in a regular screen monitor against an stereoscopic Head Mounted Display (HMD); while in the second experiment we aim at detecting the effects of shading into quality perception. At each iteration of the pair-test comparisons participants pick the mesh that they think had higher quality; by the end of the experiment we compile a preference matrix. The matrix evidences the correlation between real quality and assessed quality. Regarding the shading mode, we find an interaction with quality and shading when the model has high definition. Furthermore, we assess the subjective realism of the most/least preferred scans using an Immersive Augmented Reality (IAR) video-see-through setup. Results show higher levels of realism were perceived through the HMD than when using a monitor, although the quality was similarly perceived in both systems.