arXiv subjects

Dawar Khan

Publications and source records attributed to Dawar Khan.

8 recordsLinked to original sources

arXiv2026

ClickAIXR: On-Device Multimodal Vision-Language Interaction with Real-World Objects in Extended Reality

We present ClickAIXR, a novel on-device framework for multimodal vision-language interaction with objects in extended reality (XR). Unlike prior systems that rely on cloud-based AI (e.g., ChatGPT) or gaze-based selection (e.g., GazePointAR), ClickAIXR integrates an on-device vision-language model (VLM) with a controller-based object selection paradigm, enabling users to precisely click on real-world objects in XR. Once selected, the object image is processed locally by the VLM to answer natural language questions through both text and speech. This object-centered interaction reduces ambiguity inherent in gaze- or voice-only interfaces and improves transparency by performing all inference on-device, addressing concerns around privacy and latency. We implemented ClickAIXR in the Magic Leap SDK (C API) with ONNX-based local VLM inference. We conducted a user study comparing ClickAIXR with Gemini 2.5 Flash and ChatGPT 5, evaluating usability, trust, and user satisfaction. Results show that latency is moderate and user experience is acceptable. Our findings demonstrate the potential of click-based object selection combined with on-device AI to advance trustworthy, privacy-preserving XR interactions. The source code and supplementary materials are available at: nanovis.org/ClickAIXR.html

cs.CV↗

arXiv2025

GHAR: GeoPose-based Handheld Augmented Reality for Architectural Positioning, Manipulation and Visual Exploration

Handheld Augmented Reality (HAR) is revolutionizing the civil infrastructure application domain. The current trend in HAR relies on marker tracking technology. However, marker-based systems have several limitations, such as difficulty in use and installation, sensitivity to light, and marker design. In this paper, we propose a markerless HAR framework with GeoPose-based tracking. We use different gestures for manipulation and achieve 7 DOF (3 DOF each for translation and rotation, and 1 DOF for scaling). The proposed framework, called GHAR, is implemented for architectural building models. It augments virtual CAD models of buildings on the ground, enabling users to manipulate and visualize an architectural model before actual construction. The system offers a quick view of the building infrastructure, playing a vital role in requirement analysis and planning in construction technology. We evaluated the usability, manipulability, and comprehensibility of the proposed system using a standard user study with the System Usability Scale (SUS) and Handheld Augmented Reality User Study (HARUS). We compared our GeoPose-based markerless HAR framework with a marker-based HAR framework, finding significant improvement in the aforementioned three parameters with the markerless framework.

cs.GR↗

arXiv2025

AIvaluateXR: An Evaluation Framework for on-Device AI in XR with Benchmarking Results

The deployment of large language models (LLMs) on extended reality (XR) devices has great potential to advance the field of human-AI interaction. In the case of direct, on-device model inference, selecting the appropriate model and device for specific tasks remains challenging. In this paper, we present AIvaluateXR, a comprehensive evaluation framework for benchmarking LLMs running on XR devices. To demonstrate the framework, we deploy 17 selected LLMs across four XR platforms: Magic Leap 2, Meta Quest 3, Vivo X100s Pro, and Apple Vision Pro, and conduct an extensive evaluation. Our experimental setup measures four key metrics: performance consistency, processing speed, memory usage, and battery consumption. For each of the 68 model-device pairs, we assess performance under varying string lengths, batch sizes, and thread counts, analyzing the trade-offs for real-time XR applications. We propose a unified evaluation method based on the 3D Pareto Optimality theory to select the optimal device-model pairs from quality and speed objectives. Additionally, we compare the efficiency of on-device LLMs with client-server and cloud-based setups, and evaluate their accuracy on two interactive tasks. We believe our findings offer valuable insight to guide future optimization efforts for LLM deployment on XR devices. Our evaluation method can be used as standard groundwork for further research and development in this emerging field. The source code and supplementary materials are available at: www.nanovis.org/AIvaluateXR.html

cs.DC↗

arXiv2024

Investigation of 90,92Zr(n,{\gamma}) 91,93Zr in the s process nucleosynthesis

The neutron capture rates and Maxwellian averaged cross sections (MACS) for 90Zr(n,{\gamma}) 91Zr and 92Zr(n,{\gamma}) 93Zr processes have been computed within the framework of Talys v1.96. The effects of phenomenological nuclear level density (NLD) parameters and the gamma strength functions (GSFs) on Maxwellian averaged cross sections and neutron capture rates are examined both quantitatively and qualitatively. The present model based computed data for MACS and reaction rates gives a good comparison with the existing literature. The fine-tuning of the statistical models nuclear properties (level density and gamma-ray strength) to reproduce experimental data will allow the detailed investigation of the s process network.

nucl-th↗

arXiv2024

Biomedical Image Segmentation: A Systematic Literature Review of Deep Learning Based Object Detection Methods

Biomedical image segmentation plays a vital role in diagnosis of diseases across various organs. Deep learning-based object detection methods are commonly used for such segmentation. There exists an extensive research in this topic. However, there is no standard review on this topic. Existing surveys often lack a standardized approach or focus on broader segmentation techniques. In this paper, we conducted a systematic literature review (SLR), collected and analysed 148 articles that explore deep learning object detection methods for biomedical image segmentation. We critically analyzed these methods, identified the key challenges, and discussed the future directions. From the selected articles we extracted the results including the deep learning models, targeted imaging modalities, targeted diseases, and the metrics for the analysis of the methods. The results have been presented in tabular and/or charted forms. The results are presented in three major categories including two stage detection models, one stage detection models and point-based detection models. Each article is individually analyzed along with its pros and cons. Finally, we discuss open challenges, potential benefits, and future research directions. This SLR aims to provide the research community with a quick yet deeper understanding of these segmentation models, ultimately facilitating the development of more powerful solutions for biomedical image analysis.

eess.IV↗

arXiv2024

MidSurfer: A Parameter-Free Approach for Mid-Surface Extraction from Segmented Volumetric Data

In the field of volumetric data processing and analysis, extracting mid-surfaces from thinly bounded compartments is crucial for tasks such as surface area estimation and accurate modeling of biological structures, yet it has lacked a standardized approach. To bridge this gap, we introduce MidSurfer--a novel parameter-free method for extracting mid-surfaces from segmented volumetric data. Our method produces smooth, uniformly triangulated meshes that accurately capture the structural features of interest. The process begins with the Ridge Field Transformation step that transforms the segmented input data, followed by the Mid-Polyline Extraction Algorithm that works on individual volume slices. Based on the connectivity of components, this step can result in either single or multiple polyline segments that represent the structural features. These segments form a coherent series across the volume, creating a backbone of regularly distributed points on each slice that represents the mid-surface. Subsequently, we employ a Polyline Zipper Algorithm for triangulation that connects these polyline segments across neighboring slices, yielding a detailed triangulated mid-surface mesh. Our findings demonstrate that this method surpasses previous techniques in versatility, simplicity of use, and accuracy. Our approach is now publicly available as a plugin for ParaView, a widely-used multi-platform tool for data analysis and visualization, and can be found at https://github.com/kaust-vislab/MidSurfer .

cs.GR↗

arXiv2024

DiffFit: Visually-Guided Differentiable Fitting of Molecule Structures to a Cryo-EM Map

We introduce DiffFit, a differentiable algorithm for fitting protein atomistic structures into an experimental reconstructed Cryo-Electron Microscopy (cryo-EM) volume map. In structural biology, this process is necessary to semi-automatically composite large mesoscale models of complex protein assemblies and complete cellular structures that are based on measured cryo-EM data. The current approaches require manual fitting in three dimensions to start, resulting in approximately aligned structures followed by an automated fine-tuning of the alignment. The DiffFit approach enables domain scientists to fit new structures automatically and visualize the results for inspection and interactive revision. The fitting begins with differentiable three-dimensional (3D) rigid transformations of the protein atom coordinates followed by sampling the density values at the atom coordinates from the target cryo-EM volume. To ensure a meaningful correlation between the sampled densities and the protein structure, we proposed a novel loss function based on a multi-resolution volume-array approach and the exploitation of the negative space. This loss function serves as a critical metric for assessing the fitting quality, ensuring the fitting accuracy and an improved visualization of the results. We assessed the placement quality of DiffFit with several large, realistic datasets and found it to be superior to that of previous methods. We further evaluated our method in two use cases: automating the integration of known composite structures into larger protein complexes and facilitating the fitting of predicted protein domains into volume densities to aid researchers in identifying unknown proteins. We implemented our algorithm as an open-source plugin (github.com/nanovis/DiffFit) in ChimeraX, a leading visualization software in the field. All supplemental materials are available at osf.io/5tx4q.

q-bio.QM↗

arXiv2023

Dr. KID: Direct Remeshing and K-set Isometric Decomposition for Scalable Physicalization of Organic Shapes

Dr. KID is an algorithm that uses isometric decomposition for the physicalization of potato-shaped organic models in a puzzle fashion. The algorithm begins with creating a simple, regular triangular surface mesh of organic shapes, followed by iterative k-means clustering and remeshing. For clustering, we need similarity between triangles (segments) which is defined as a distance function. The distance function maps each triangle's shape to a single point in the virtual 3D space. Thus, the distance between the triangles indicates their degree of dissimilarity. K-means clustering uses this distance and sorts of segments into k classes. After this, remeshing is applied to minimize the distance between triangles within the same cluster by making their shapes identical. Clustering and remeshing are repeated until the distance between triangles in the same cluster reaches an acceptable threshold. We adopt a curvature-aware strategy to determine the surface thickness and finalize puzzle pieces for 3D printing. Identical hinges and holes are created for assembling the puzzle components. For smoother outcomes, we use triangle subdivision along with curvature-aware clustering, generating curved triangular patches for 3D printing. Our algorithm was evaluated using various models, and the 3D-printed results were analyzed. Findings indicate that our algorithm performs reliably on target organic shapes with minimal loss of input geometry.

cs.GR↗