arXiv subjects

Balakrishnan Prabhakaran

Publications and source records attributed to Balakrishnan Prabhakaran.

At least 19 recordsLinked to original sources

arXiv2026

ObjectSplat: Improving Mesh Fidelity and Interactivity for 3D Scenes via Object-Level Mesh Splatting

Splatting-based algorithms reconstruct photorealistic, real-time-renderable, and mesh-exportable 3D scenes from regular images, but they represent a scene as a single monolithic field. Therefore, the reconstruction has no object-level structure, leaving it infeasible for downstream editing or interaction. Moreover, regions that are never directly observed in the input scans are contaminated by the surrounding texture and left uncorrected, capping both mesh fidelity and novel-view synthesis. We propose a decompose-before-reconstruct approach: we segment the instances out of every frame, consider the remaining as background and inpaint it, reconstruct each instance and the background independently with mesh splatting, and compose them into a single scene. Our method significantly improves mesh fidelity (over a 5\% gain in F-score) and novel-view synthesis, while supporting object-wise modifiability and interactivity. The code will be made publicly available.

cs.CV↗

arXiv2026

CustomDance: Customized 3D Dance Generation with Coarse-to-Fine Human-Centered Interactive Control

With the rise of AI-generated content (AIGC) and advanced techniques for 3D human representation, the task of generating 3D dance movements has become an exciting area of research. Despite significant advancements, current methods often fail to provide comprehensive and distinct control over various multimodal inputs from users, such as music or specific descriptions of desired movements. As a result, the generated motions may be statistically plausible and technically correct, but they often lack depth, expressiveness, and alignment with the user's creative vision. To address this issue, we present CustomDance, a coarse-to-fine interactive system designed for customized 3D dance generation. Inspired by the workflows of expert choreographers, CustomDance introduces a novel paradigm to AI-assisted choreography through three interconnected stages. First, a multimodal Large Language Model (MLLM) analyzes the music and a high-level text prompt to identify key temporal anchors and creative cues for the piece. Next, for each anchor, a multimodal retriever suggests high-quality motion clips from a dance library based on local music and text, empowering the user with concrete and predictable options. Finally, a custom music-conditioned diffusion in-painter seamlessly connects the selected phrases, allowing for iterative, user-guided refinement of the final composition, supported by visualizations of motion dynamics. Our evaluations demonstrate that CustomDance not only highlights the significant creative utility and empowering potential of our AI-assisted choreography paradigm, but also outperforms competitive baselines across quantitative and qualitative comparisons. Project page: https://github.com/XulongT/CustomDance

cs.HC↗

arXiv2026

CAOA -- Completion-Assisted Object-CAD Alignment

Accurately aligning CAD models to their corresponding objects in indoor RGB-D scans is a central challenge in 3D semantic reconstruction. The task requires estimating a 9-Degree-of-Freedom (DoF) pose-position, rotation, and scale along three axes-but is hindered by noisy and incomplete scans, as well as segmentation errors that cause geometric distortions. We present Completion-Assisted Object-CAD Alignment (CAOA), a method that integrates a semantically and contextually aware point cloud completion module with a symmetry-aware relative pose estimation algorithm, enabling precise alignment of CAD models to scanned objects. Existing completion methods are typically trained and evaluated on synthetic datasets, which often fail to generalize to real-world scans. To bridge this gap, we introduce a synthetic data generation strategy tailored to indoor scenes, significantly reducing the synthetic-to-real domain gap-validated through quantitative comparisons with widely used completion datasets. In addition, we release S2C-Completion, an expert-annotated dataset of over 8,500 object-CAD pairs from Scan2CAD, created for real-world indoor single-object completion and intended as a new benchmark for this task. For object-CAD alignment, we incorporate symmetry information via a symmetry-aware loss, improving robustness to symmetric ambiguities. On the Scan2CAD benchmark, CAOA achieves a 17% accuracy improvement over state-of-the-art methods.

cs.CV↗

arXiv2026

A Survey on Deep Learning Architectures for Point Cloud Classification and Segmentation

Point cloud stands as the most widely adopted format for representing 3D shapes and scenes due to its simplicity and geometric fidelity. However, its inherent unordered and irregular nature, exacerbated by sensor noise and occlusions, introduces unique challenges for machine learning based methodologies. To combat these issues, diverse strategies have been developed, including converting to a format that has orderliness, extracting local geometry, and permutation-invariant or self-attention-based processing. In this paper, our focus is directed towards deep learning models for three fundamental tasks in 3D vision: point cloud classification, part segmentation, and semantic segmentation. We begin by formally defining point cloud data, followed by an in-depth discussion on its structural characteristics. Then, we categorize notable works based on their backbone structure and evaluate their performance on popular benchmarks. Beyond empirical comparison, we offer insights into architectural innovations and limitations. We also outline open challenges and promising future directions for 3D point cloud understanding.

cs.CV↗

arXiv2026

Weight Group-wise Post-Training Quantization for Medical Foundation Model

Foundation models have achieved remarkable results in medical image analysis. However, its large network architecture and high computational complexity significantly impact inference speed, limiting its application on terminal medical devices. Quantization, a technique that compresses models into low-bit versions, is a solution to this challenge. In this paper, we propose a post-training quantization algorithm, Permutation-COMQ. It eliminates the need for backpropagation by using simple dot products and rounding operations, thereby removing hyperparameter tuning and simplifying the process. Additionally, we introduce a weight-aware strategy that reorders the weight within each layer to address the accuracy degradation induced by channel-wise scaling during quantization, while preserving channel structure. Experiments demonstrate that our method achieves the best results in 2-bit, 4-bit, and 8-bit quantization.

cs.CV↗

arXiv2026

Evidence-Based Actor-Verifier Reasoning for Echocardiographic Agents

Echocardiography plays an important role in the screening and diagnosis of cardiovascular diseases. However, automated intelligent analysis of echocardiographic data remains challenging due to complex cardiac dynamics and strong view heterogeneity. In recent years, visual language models (VLM) have opened a new avenue for building ultrasound understanding systems for clinical decision support. Nevertheless, most existing methods formulate this task as a direct mapping from video and question to answer, making them vulnerable to template shortcuts and spurious explanations. To address these issues, we propose EchoTrust, an evidence-driven Actor-Verifier framework for trustworthy reasoning in echocardiography VLM-based agents. EchoTrust produces a structured intermediate representation that is subsequently analyzed by distinct roles, enabling more reliable and interpretable decision-making for high-stakes clinical applications.

cs.CV↗

arXiv2025

IntelliCardiac: An Intelligent Platform for Cardiac Image Segmentation and Classification

Precise and effective processing of cardiac imaging data is critical for the identification and management of the cardiovascular diseases. We introduce IntelliCardiac, a comprehensive, web-based medical image processing platform for the automatic segmentation of 4D cardiac images and disease classification, utilizing an AI model trained on the publicly accessible ACDC dataset. The system, intended for patients, cardiologists, and healthcare professionals, offers an intuitive interface and uses deep learning models to identify essential heart structures and categorize cardiac diseases. The system supports analysis of both the right and left ventricles as well as myocardium, and then classifies patient's cardiac images into five diagnostic categories: dilated cardiomyopathy, myocardial infarction, hypertrophic cardiomyopathy, right ventricular abnormality, and no disease. IntelliCardiac combines a deep learning-based segmentation model with a two-step classification pipeline. The segmentation module gains an overall accuracy of 92.6%. The classification module, trained on characteristics taken from segmented heart structures, achieves 98% accuracy in five categories. These results exceed the performance of the existing state-of-the-art methods that integrate both segmentation and classification models. IntelliCardiac, which supports real-time visualization, workflow integration, and AI-assisted diagnostics, has great potential as a scalable, accurate tool for clinical decision assistance in cardiac imaging and diagnosis.

eess.IV↗

arXiv2025

RobotFingerPrint: Unified Gripper Coordinate Space for Multi-Gripper Grasp Synthesis and Transfer

We introduce a novel grasp representation named the Unified Gripper Coordinate Space (UGCS) for grasp synthesis and grasp transfer. Our representation leverages spherical coordinates to create a shared coordinate space across different robot grippers, enabling it to synthesize and transfer grasps for both novel objects and previously unseen grippers. The strength of this representation lies in the ability to map palm and fingers of a gripper and the unified coordinate space. Grasp synthesis is formulated as predicting the unified spherical coordinates on object surface points via a conditional variational autoencoder. The predicted unified gripper coordinates establish exact correspondences between the gripper and object points, which is used to optimize grasp pose and joint values. Grasp transfer is facilitated through the point-to-point correspondence between any two (potentially unseen) grippers and solved via a similar optimization. Extensive simulation and real-world experiments showcase the efficacy of the unified grasp representation for grasp synthesis in generating stable and diverse grasps. Similarly, we showcase real-world grasp transfer from human demonstrations across different objects.

cs.RO↗

arXiv2024

MultiGripperGrasp: A Dataset for Robotic Grasping from Parallel Jaw Grippers to Dexterous Hands

We introduce a large-scale dataset named MultiGripperGrasp for robotic grasping. Our dataset contains 30.4M grasps from 11 grippers for 345 objects. These grippers range from two-finger grippers to five-finger grippers, including a human hand. All grasps in the dataset are verified in the robot simulator Isaac Sim to classify them as successful and unsuccessful grasps. Additionally, the object fall-off time for each grasp is recorded as a grasp quality measurement. Furthermore, the grippers in our dataset are aligned according to the orientation and position of their palms, allowing us to transfer grasps from one gripper to another. The grasp transfer significantly increases the number of successful grasps for each gripper in the dataset. Our dataset is useful to study generalized grasp planning and grasp transfer across different grippers. Data, code and videos for the project are available at https://irvlutd.github.io/MultiGripperGrasp

cs.RO↗

arXiv2024

SCENEREPLICA: Benchmarking Real-World Robot Manipulation by Creating Replicable Scenes

We present a new reproducible benchmark for evaluating robot manipulation in the real world, specifically focusing on pick-and-place. Our benchmark uses the YCB objects, a commonly used dataset in the robotics community, to ensure that our results are comparable to other studies. Additionally, the benchmark is designed to be easily reproducible in the real world, making it accessible to researchers and practitioners. We also provide our experimental results and analyzes for model-based and model-free 6D robotic grasping on the benchmark, where representative algorithms are evaluated for object perception, grasping planning, and motion planning. We believe that our benchmark will be a valuable tool for advancing the field of robot manipulation. By providing a standardized evaluation framework, researchers can more easily compare different techniques and algorithms, leading to faster progress in developing robot manipulation methods.

cs.RO↗

arXiv2023

Experiences with CAMRE: Single-Device Collaborative Adaptive Mixed Reality Environment

During collaboration in XR (eXtended Reality), users typically share and interact with virtual objects in a common, shared virtual environment. Specifically, collaboration among users in Mixed Reality (MR) requires knowing their position, movement, and understanding of the visual scene surrounding their physical environments. Otherwise, one user could move an important virtual object to a position blocked by the physical environment for others. However, even for a single physical environment, 3D reconstruction takes a long time and the produced 3D data is typically very large in size. Also, these large amounts of 3D data take a long time to be streamed to receivers making real-time updates on the rendered scene challenging. Furthermore, many collaboration systems in MR require multiple devices, which take up space and make setup difficult. To address these challenges, in this paper, we describe a single-device system called Collaborative Adaptive Mixed Reality Environment (CAMRE). We build CAMRE using the scene understanding capabilities of HoloLens 2 devices to create shared MR virtual environments for each connected user and demonstrate using a Leader-Follower(s) paradigm: faster reconstruction and scene update times due to smaller data. Consequently, multiple users can receive shared, synchronized, and close-to-real-time latency virtual scenes from a chosen Leader, based on their physical position and movement. We also illustrate other expanded features of CAMRE MR virtual environment such as navigation using a real-time virtual mini-map and X-ray vision for handling adaptive wall opacity. We share several experimental results that evaluate the performance of CAMRE in terms of the network latency in sharing virtual objects and other capabilities.

cs.HC↗

arXiv2023

Assessment HTN (A-HTN) for Automated Task Performance Assessment in 3D Serious Games

In the recent years, various 3D mixed reality serious games have been developed for different applications such as physical training, rehabilitation, and education. Task performance in a serious game is a measurement of how efficiently and accurately users accomplish the game's objectives. Prior research includes a graph-based representation of tasks, e.g. Hierarchical Task Network (HTN), which only models a game's tasks but does not perform assessment. In this paper, we propose Assessment HTN (A-HTN), which both models the task efficiently and incorporates assessment logic for game objectives. Based on how the task performance is evaluated, A-HTN automatically performs: (a) Task-level Assessment by comparing object manipulations and (b) Action-level Assessment by comparing motion trajectories. The system can also categorize the task performance assessment into single user or multi-user based on who is being assessed. We showcase the effectiveness of the A-HTN using two 3D VR serious games: a hydrometer experiment and a multi-user chemistry experiment. The A-HTN experiments show a high correlation between instructor scores and the system generated scores indicating that the proposed A-HTN generalizes automatic assessment at par with Subject Matter Experts.

cs.HC↗

arXiv2022

Augmented Reality and Mixed Reality Measurement Under Different Environments: A Survey on Head-Mounted Devices

Augmented Reality (AR) and Mixed Reality (MR) have been two of the most explosive research topics in the last few years. Head-Mounted Devices (HMDs) are essential intermediums for using AR and MR technology, playing an important role in the research progress in these two areas. Behavioral research with users is one way of evaluating the technical progress and effectiveness of HMDs. In addition, AR and MR technology is dependent upon virtual interactions with the real environment. Thus, conditions in real environments can be a significant factor for AR and MR measurements with users. In this paper, we survey 87 environmental-related HMD papers with measurements from users, spanning over 32 years. We provide a thorough review of AR- and MR-related user experiments with HMDs under different environmental factors. Then, we summarize trends in this literature over time using a new classification method with four environmental factors, the presence or absence of user feedback in behavioral experiments, and ten main categories to subdivide these papers (e.g., domain and method of user assessment). We also categorize characteristics of the behavioral experiments, showing similarities and differences among papers.

cs.HC↗

arXiv2022

Dynamic X-Ray Vision in Mixed Reality

X-ray vision, a technique that allows users to see through walls and other obstacles, is a popular technique for Augmented Reality (AR) and Mixed Reality (MR). In this paper, we demonstrate a dynamic X-ray vision window that is rendered in real-time based on the user's current position and changes with movement in the physical environment. Moreover, the location and transparency of the window are also dynamically rendered based on the user's eye gaze. We build this X-ray vision window for a current state-of-the-art MR Head-Mounted Device (HMD) -- HoloLens 2 by integrating several different features: scene understanding, eye tracking, and clipping primitive.

cs.HC↗

arXiv2022

HoloLens 2 Technical Evaluation as Mixed Reality Guide

Mixed Reality (MR) is an evolving technology lying in the continuum spanned by related technologies such as Virtual Reality (VR) and Augmented Reality (AR), and creates an exciting way of interacting with people and the environment. This technology is fast becoming a tool used by many people, potentially improving living environments and work efficiency. Microsoft HoloLens has played an important role in the progress of MR, from the first generation to the second generation. In this paper, we systematically evaluate the functions of applicable functions in HoloLens 2. These evaluations can serve as a performance benchmark that can help people who need to use this instrument for research or applications in the future. The detailed tests and the performance evaluation of the different functionalities show the usability and possible limitations of each function. We mainly divide the experiment into the existing functions of the HoloLens 1, the new functions of the HoloLens 2, and the use of research mode. This research results will be useful for MR researchers who want to use HoloLens 2 as a research tool to design their own MR applications.

cs.HC↗

arXiv2022

NeuralGrasps: Learning Implicit Representations for Grasps of Multiple Robotic Hands

We introduce a neural implicit representation for grasps of objects from multiple robotic hands. Different grasps across multiple robotic hands are encoded into a shared latent space. Each latent vector is learned to decode to the 3D shape of an object and the 3D shape of a robotic hand in a grasping pose in terms of the signed distance functions of the two 3D shapes. In addition, the distance metric in the latent space is learned to preserve the similarity between grasps across different robotic hands, where the similarity of grasps is defined according to contact regions of the robotic hands. This property enables our method to transfer grasps between different grippers including a human hand, and grasp transfer has the potential to share grasping skills between robots and enable robots to learn grasping skills from humans. Furthermore, the encoded signed distance functions of objects and grasps in our implicit representation can be used for 6D object pose estimation with grasping contact optimization from partial point clouds, which enables robotic grasping in the real world.

cs.RO↗

arXiv2022

Core-set Selection Using Metrics-based Explanations (CSUME) for multiclass ECG

The adoption of deep learning-based healthcare decision support systems such as the detection of irregular cardiac rhythm is hindered by challenges such as lack of access to quality data and the high costs associated with the collection and annotation of data. The collection and processing of large volumes of healthcare data is a continuous process. The performance of data-hungry Deep Learning models (DL) is highly dependent on the quantity and quality of the data. While the need for data quantity has been established through research adequately, we show how a selection of good quality data improves deep learning model performance. In this work, we take Electrocardiogram (ECG) data as a case study and propose a model performance improvement methodology for algorithm developers, that selects the most informative data samples from incoming streams of multi-class ECG data. Our Core-Set selection methodology uses metrics-based explanations to select the most informative ECG data samples. This also provides an understanding (for algorithm developers) as to why a sample was selected as more informative over others for the improvement of deep learning model performance. Our experimental results show a 9.67% and 8.69% precision and recall improvement with a significant training data volume reduction of 50%. Additionally, our proposed methodology asserts the quality and annotation of ECG samples from incoming data streams. It allows automatic detection of individual data samples that do not contribute to model learning thus minimizing possible negative effects on model performance. We further discuss the potential generalizability of our approach by experimenting with a different dataset and deep learning architecture.

cs.LG↗

arXiv2022

A wearable sensor vest for social humanoid robots with GPGPU, IoT, and modular software architecture

Currently, most social robots interact with their surroundings and humans through sensors that are integral parts of the robots, which limits the usability of the sensors, human-robot interaction, and interchangeability. A wearable sensor garment that fits many robots is needed in many applications. This article presents an affordable wearable sensor vest, and an open-source software architecture with the Internet of Things (IoT) for social humanoid robots. The vest consists of touch, temperature, gesture, distance, vision sensors, and a wireless communication module. The IoT feature allows the robot to interact with humans locally and over the Internet. The designed architecture works for any social robot that has a general-purpose graphics processing unit (GPGPU), I2C/SPI buses, Internet connection, and the Robotics Operating System (ROS). The modular design of this architecture enables developers to easily add/remove/update complex behaviors. The proposed software architecture provides IoT technology, GPGPU nodes, I2C and SPI bus mangers, audio-visual interaction nodes (speech to text, text to speech, and image understanding), and isolation between behavior nodes and other nodes. The proposed IoT solution consists of related nodes in the robot, a RESTful web service, and user interfaces. We used the HTTP protocol as a means of two-way communication with the social robot over the Internet. Developers can easily edit or add nodes in C, C++, and Python programming languages. Our architecture can be used for designing more sophisticated behaviors for social humanoid robots.

cs.RO↗