Eric J. Gonzalez

Eye gaze has become an essential input for spatial computing, but its coarse targeting and saccadic nature limit precision and complicate continuous interactions such as dragging, especially under user motion. Gaze+pinch has also become standard in XR for its convenience, yet mid-air gestures remain imprecise, fatiguing, and socially unacceptable. These limitations underscore the need for an approach that preserves the speed of gaze while enabling stable, fine control. We present GazeTune, a cascaded multimodal interaction technique combining gaze and touch to refine gaze-based selection and manipulation. Touch serves as a refinement channel within gaze pointing, allowing precise cursor and target control. Our work investigates how gaze-and-touch enhances dragging and mitigates Motion-Induced instability. In a study (N=20), we compared GazeTune against gaze-only and gaze-pinch methods in 2D dragging. Results show that GazeTune achieves significantly lower error with comparable execution time, validating its effectiveness and balanced trade-off between time and accuracy.

Interacting with real-world objects in AR is difficult, especially when targets are distant, cluttered, or occluded. These challenges are amplified on emerging lightweight AR glasses, which often lack binocular or large field of view on display, but also continuous inputs, such as hand or eye tracking. Proxy-based interfaces offer an alternative by allowing users to interact with virtual abstractions of physical objects that can be repositioned, reorganized, and adapted to the task and device. However, designing such interfaces is currently manual and highly device-specific. We present Generative Proxy, a method for automatically generating proxy-based interfaces from three specifications: scene, intent, and device capabilities. We formulate generation as a constrained synthesis problem that first produces valid interfaces for the target device and task, then ranks candidates using semantic and articulatory distance inspired by direct manipulation theory. We demonstrate Generative Proxy across diverse scenes, device profiles, and user intents. Expert evaluation shows initial evidence that generated proxy UIs are useful and usable, highlighting proxy-based abstraction as a promising interaction paradigm for future AR glasses.

The proliferation of XR devices has made egocentric hand pose estimation a vital task, yet this perspective is inherently challenged by frequent finger occlusions. To address this, we propose a novel approach that leverages the rich information in dorsal hand skin deformation, unlocked by recent advances in dense visual featurizers. We introduce a dual-stream delta encoder that learns pose by contrasting features from a dynamic hand with a baseline relaxed position. Our evaluation demonstrates that, using only cropped dorsal images, our method reduces the Mean Per Joint Angle Error (MPJAE) by 18% in self-occluded scenarios (fingers (ge 50%) occluded) compared to state-of-the-art techniques that depend on the whole hand’s geometry and large model backbones. Consequently, our method not only enhances the reliability of downstream tasks like index finger pinch and tap estimation in occluded scenarios but also unlocks new interaction paradigms, such as detecting isometric force for a surface “click” without visible movement while minimizing model size. Our codebase is found at https://github.com/hilab-open-source/deltadorsal.

We present HandOver, an extended reality (XR) interaction technique designed to unify the precision of traditional mouse input for object selection with the expressiveness of hand-tracking for object manipulation. With HandOver, the mouse is used to drive a depth-aware 3D cursor enabling precise and restful targeting — by hovering their hand over the mouse, the user can then seamlessly transition into direct 3D manipulation of the target object. In a formal user study, we compare HandOver against two ray-based techniques: traditional raycasting (Ray) and a hybrid method (Ray+Hand) in a 3D docking task. Results show HandOver yields lower task errors across all distances, and moreover improves interaction ergonomics as highlighted by a RULA posture analysis and self-reported measures (NASA-TLX). These findings illustrate the benefits of blending traditional precise input devices with the expressive gestural inputs afforded by hand-tracking in XR, leading to improved user comfort and task performance. This blended paradigm yields a unified workflow allowing users to leverage the best of each input modality as they interact in immersive environments.

Spatial interaction in 3D environments requires balancing efficiency and precision, which requires dynamic tracking speed adjustments. However, existing techniques often couple tracking speed adjustments directly with hand movements, reducing interaction flexibility. Inspired by the natural friction control inherent in the physical world, we introduce ForcePinch, a novel force-responsive spatial interaction method that enables users to intuitively modulate pointer tracking speed and smoothly transition between rapid and precise movements by varying their pinching force. To implement this concept, we developed a hardware prototype integrating a pressure sensor with a customizable mapping function that translates pinching force into tracking speed adjustments. We conducted a user study with 20 participants performing well-established 1D, 2D, and 3D object manipulation tasks, comparing ForcePinch against the distance-responsive technique Go-Go and speed-responsive technique PRISM. Results highlight distinctive characteristics of the force-responsive approach across different interaction contexts. Drawing on these findings, we highlight the contextual meaning and versatility of force-responsive interactions through four illustrative examples, aiming to inform and inspire future spatial interaction design.

Innovations in spatial computing and artificial intelligence (AI) are making it possible to overlay dynamic, interactive digital elements on the physical world. Soon, every object might have a real-time digital twin, enabling the “Internet of Things” so as to identify and interact with even unconnected items. This programmable reality would enable computational manipulation of the world around us through alteration of its appearance or functionality, similar to software, but for reality itself. Advances in AI language models have enabled zero-shot segmentation and understanding of the world, making it possible to query and manipulate objects with precision. However, this vision also demands natural and intuitive ways for humans to interact with these models through gestures, gaze, and existing devices. Augmented reality (AR) provides the ideal bridge between AI output and human input in the physical world. Moreover, diffusion models and physics simulations offer exciting possibilities for content generation and editing, allowing us to transform everyday activities into extraordinary experiences. As AR devices become ubiquitous and indistinguishable from reality, these technologies blur the lines between reality and simulations. This raises profound questions about how we perceive and experience the world while having implications for memory, learning, and even behavior. Programmable reality enabled by AR and AI has vast potential to reshape our relationships with the digital realm, ultimately making it an extension of the physical realm.

Hand raycasting is widely used in extended reality (XR) for selection and interaction, but prolonged use can lead to arm fatigue (e.g., "gorilla arm"). Traditional techniques often require a large range of motion where the arm is extended and unsupported, exacerbating this issue. In this paper, we explore hand raycast techniques aimed at reducing arm fatigue, while minimizing impact to precision selection. In particular, we present Joint-Amplified Raycasting (JAR) – a technique which scales and combines the orientations of multiple joints in the arm to enable more ergonomic raycasting. Through a comparative evaluation with the commonly used industry standard Shoulder-Palm Raycast (SP) and two other ergonomic alternatives—Offset Shoulder-Palm Raycast (OSP) and Wrist-Palm Raycast (WP)—we demonstrate that JAR results in higher selection throughput and reduced fatigue. A follow-up study highlights the effects of different JAR joint gains on target selection and shows users prefer JAR over SP in a representative UI task.

Unlike other inputs for extended reality (XR) that work out of the box, eye tracking typically requires custom calibration per user or session. We present a multimodal inputs approach for implicit calibration of eye tracker in VR, leveraging UI interaction for continuous, background calibration. Our method analyzes gaze data alongside controller interaction with UI elements, and employing ML techniques it continuously refines the calibration matrix without interrupting users from their current tasks. Potentially eliminating the need for explicit calibration. We demonstrate the accuracy and effectiveness of this implicit approach across various tasks and real time applications achieving comparable eye tracking accuracy to native, explicit calibration. While our evaluation focuses on VR and controller-based interactions, we anticipate the broader applicability of this approach to various XR devices and input modalities.