arXiv subjects

Chuong Nguyen

Publications and source records attributed to Chuong Nguyen.

At least 19 recordsLinked to original sources

arXiv2026

Certified Spherical MUSIC for 3D Localization under Adversarial Subspace Perturbations

We study an oracle subspace-perturbation model in which the 3D localization procedure is given an $s$-dimensional subspace $\widetilde{\mathcal U}$ and a deterministic error bound $\eps_{\rm sub}$ measuring the sine-theta distance between $\widetilde{\mathcal U}$ and an $s$-dimensional subspace $\cU$ of far-field patterns with wavenumber $\kappa$. Under explicit arbitrary-cloud separation and conditioning hypotheses, we prove that the perturbed spherical MUSIC objective \[ \widetilde q(\bz) = 1-\|P_{\widetilde{\mathcal U}}\varphi_\bz\|_2^2 \] has a unique strongly convex well in each ball $B_{\gamma/\kappa}(x_j)$ and the objective has a uniform value gap outside the union of the certified wells. A fixed-step gradient map with $h\asymp\kappa^{-2}$ leaves every certified well invariant and converges linearly to its unique minimizer. Consequently, thresholding on an $O(\kappa^{-1})$-mesh, followed by gradient descent from all accepted grid points and duplicate removal, recovers all relevant minima. The arbitrary-cloud frame analysis gives the sufficient condition \[ \kappa\delta_X\gtrsim s^{2/3} \] through an absolute coherence row sum and Gershgorin's theorem. We also construct lower-frame counterexamples below the $s^{1/6}$ scale, upper-frame counterexamples below the $s^{1/3}$ scale, and examples showing that the exponent $2/3$ is optimal for the absolute-row-sum argument. The latter is a sharpness result for the proof method and is not a spectral necessity claim. Finally, for parameter classes containing a uniformly admissible one-point displacement path, we prove that the deterministic oracle localization modulus is \[ \mathfrak R(\eps) \asymp \frac{\eps}{\kappa}. \]

math.CA↗

arXiv2026

MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model

Human-Object Interaction (HOI) video reenactment aims to transfer the interaction dynamics of a source video to a novel target object while preserving realistic hand-object coordination. Existing methods typically rely on sparse 2D motion controls and monocular references, which are insufficient for complex out-of-plane motion and large viewpoint changes. We present MVHOI, a two-stage framework combining implicit motion extraction, 3D-aware multi-view reasoning, and video generation. In the first stage, a motion extractor encodes object dynamics into implicit motion descriptors. Conditioned on these descriptors, our Motion-Driven Object Prior (MDOP) module queries a 3D foundation model over multi-view references of the target object and autoregressively predicts coarse object anchors, a sequence of images that track the object's evolving orientation and appearance under the source motion without any explicit pose estimation. In the second stage, a DiT-based video generation model uses these anchors as structural guidance and the multi-view references as appearance guidance. We further reuse cross-view attention from MDOP as a soft attention bias to reduce reference-view confusion. For long videos, a cross-iterative inference strategy refreshes subsequent object priors using refined video outputs. Experiments demonstrate consistent improvements over state-of-the-art methods in object fidelity, motion consistency, visual quality, and interaction realism.

cs.CV↗

arXiv2026

Bridging Human Interpretation and Machine Representation: A Landscape of Qualitative Data Analysis in the LLM Era

LLMs are increasingly used to support qualitative research, yet existing systems produce outputs that vary widely--from trace-faithful summaries to theory-mediated explanations and system models. To make these differences explicit, we introduce a 4$\times$4 landscape crossing four levels of meaning-making (descriptive, categorical, interpretive, theoretical) with four levels of modeling (static structure, stages/timelines, causal pathways, feedback dynamics). Applying the landscape to prior LLM-based automation highlights a strong skew toward low-level meaning and low-commitment representations, with few reliable attempts at interpretive/theoretical inference or dynamical modeling. Based on the revealed gap, we outline an agenda for applying and building LLM-systems that make their interpretive and modeling commitments explicit, selectable, and governable.

cs.CL↗

arXiv2025

LOGOS: LLM-driven End-to-End Grounded Theory Development and Schema Induction for Qualitative Research

Grounded theory offers deep insights from qualitative data, but its reliance on expert-intensive manual coding presents a major scalability bottleneck. Existing computational tools either fail on full automation or lack flexible schema construction. We introduce LOGOS, a novel, end-to-end framework that fully automates the grounded theory workflow, transforming raw text into a structured, hierarchical theory. LOGOS integrates LLM-driven coding, semantic clustering, graph reasoning, and a novel iterative refinement process to build highly reusable codebooks. To ensure fair comparison, we also introduce a principled 5-dimensional metric and a train-test split protocol for standardized, unbiased evaluation. Across five diverse corpora, LOGOS consistently outperforms strong baselines and achieves a remarkable average $80.4\%$ alignment with an expert-developed schema on complex datasets. LOGOS demonstrates a potential to democratize and scale qualitative research without sacrificing theoretical nuance.

cs.CL↗

arXiv2025

Mitigating Multimodal Hallucinations via Gradient-based Self-Reflection

Multimodal large language models achieve strong performance across diverse tasks but remain prone to hallucinations, where outputs are not grounded in visual inputs. This issue can be attributed to two main biases: text-visual bias, the overreliance on prompts and prior outputs, and co-occurrence bias, spurious correlations between frequently paired objects. We propose Gradient-based Influence-Aware Constrained Decoding (GACD), an inference-based method, that addresses both biases without auxiliary models, and is readily applicable to existing models without finetuning. The core of our approach is bias estimation, which uses first-order Taylor gradients to understand the contribution of individual tokens-visual features and text tokens-to the current output. Based on this analysis, GACD mitigates hallucinations through two components: (1) suppressing spurious visual features correlated with the output objects, and (2) rebalancing cross-modal contributions by strengthening visual features relative to text. Experiments across multiple benchmarks demonstrate that GACD effectively reduces hallucinations and improves the visual grounding of MLLM outputs.

cs.CV↗

arXiv2025

Wound3DAssist: A Practical Framework for 3D Wound Assessment

Managing chronic wounds remains a major healthcare challenge, with clinical assessment often relying on subjective and time-consuming manual documentation methods. Although 2D digital videometry frameworks have aided wound measurement, these approaches struggle with perspective distortion, a limited field of view, and an inability to capture wound depth, especially in anatomically complex or curved regions. To overcome these limitations, we present Wound3DAssist, a practical framework for 3D wound assessment using monocular consumer-grade videos. Our framework generates 3D wound models from short handheld recordings captured using consumer-grade devices, enabling non-contact, automatic measurements from reconstructed multi-view surfaces. We integrate 3D reconstruction, wound segmentation, tissue classification, and periwound analysis into a modular workflow. We evaluate Wound3DAssist across digital models with known geometry, silicone phantoms, and real patients. Results show that the framework supports high-quality wound bed visualization, approximately millimeter-scale surface reconstruction accuracy in the evaluated clinical cases, and multi-view wound-tissue composition analysis. Full assessments are completed in under 20 minutes, demonstrating feasibility for a research framework intended for future clinical workflow evaluation.

cs.CV↗

arXiv2025

DCHM: Depth-Consistent Human Modeling for Multiview Detection

Multiview pedestrian detection typically involves two stages: human modeling and pedestrian localization. Human modeling represents pedestrians in 3D space by fusing multiview information, making its quality crucial for detection accuracy. However, existing methods often introduce noise and have low precision. While some approaches reduce noise by fitting on costly multiview 3D annotations, they often struggle to generalize across diverse scenes. To eliminate reliance on human-labeled annotations and accurately model humans, we propose Depth-Consistent Human Modeling (DCHM), a framework designed for consistent depth estimation and multiview fusion in global coordinates. Specifically, our proposed pipeline with superpixel-wise Gaussian Splatting achieves multiview depth consistency in sparse-view, large-scaled, and crowded scenarios, producing precise point clouds for pedestrian localization. Extensive validations demonstrate that our method significantly reduces noise during human modeling, outperforming previous state-of-the-art baselines. Additionally, to our knowledge, DCHM is the first to reconstruct pedestrians and perform multiview segmentation in such a challenging setting. Code is available on the \href{https://jiahao-ma.github.io/DCHM/}{project page}.

cs.CV↗

arXiv2025

Efficient Depth- and Spatially-Varying Image Simulation for Defocus Deblur

Modern cameras with large apertures often suffer from a shallow depth of field, resulting in blurry images of objects outside the focal plane. This limitation is particularly problematic for fixed-focus cameras, such as those used in smart glasses, where adding autofocus mechanisms is challenging due to form factor and power constraints. Due to unmatched optical aberrations and defocus properties unique to each camera system, deep learning models trained on existing open-source datasets often face domain gaps and do not perform well in real-world settings. In this paper, we propose an efficient and scalable dataset synthesis approach that does not rely on fine-tuning with real-world data. Our method simultaneously models depth-dependent defocus and spatially varying optical aberrations, addressing both computational complexity and the scarcity of high-quality RGB-D datasets. Experimental results demonstrate that a network trained on our low resolution synthetic images generalizes effectively to high resolution (12MP) real-world images across diverse scenes.

cs.CV↗

arXiv2025

Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction

Multi-view 3D reconstruction remains a core challenge in computer vision. Recent methods, such as DUST3R and its successors, directly regress pointmaps from image pairs without relying on known scene geometry or camera parameters. However, the performance of these models is constrained by the diversity and scale of available training data. In this work, we introduce Puzzles, a data augmentation strategy that synthesizes an unbounded volume of high-quality posed video-depth data from a single image or video clip. By simulating diverse camera trajectories and realistic scene geometry through targeted image transformations, Puzzles significantly enhances data variety. Extensive experiments show that integrating Puzzles into existing video-based 3D reconstruction pipelines consistently boosts performance without modifying the underlying network architecture. Notably, models trained on only ten percent of the original data augmented with Puzzles still achieve accuracy comparable to those trained on the full dataset. Code is available at https://jiahao-ma.github.io/puzzles/.

cs.CV↗

arXiv2025

GS-2DGS: Geometrically Supervised 2DGS for Reflective Object Reconstruction

3D modeling of highly reflective objects remains challenging due to strong view-dependent appearances. While previous SDF-based methods can recover high-quality meshes, they are often time-consuming and tend to produce over-smoothed surfaces. In contrast, 3D Gaussian Splatting (3DGS) offers the advantage of high speed and detailed real-time rendering, but extracting surfaces from the Gaussians can be noisy due to the lack of geometric constraints. To bridge the gap between these approaches, we propose a novel reconstruction method called GS-2DGS for reflective objects based on 2D Gaussian Splatting (2DGS). Our approach combines the rapid rendering capabilities of Gaussian Splatting with additional geometric information from foundation models. Experimental results on synthetic and real datasets demonstrate that our method significantly outperforms Gaussian-based techniques in terms of reconstruction and relighting and achieves performance comparable to SDF-based methods while being an order of magnitude faster. Code is available at https://github.com/hirotong/GS2DGS

cs.CV↗

arXiv2024

Variable-Frequency Model Learning and Predictive Control for Jumping Maneuvers on Legged Robots

Achieving both target accuracy and robustness in dynamic maneuvers with long flight phases, such as high or long jumps, has been a significant challenge for legged robots. To address this challenge, we propose a novel learning-based control approach consisting of model learning and model predictive control (MPC) utilizing a variable-frequency scheme. Compared to existing MPC techniques, we learn a model directly from experiments, accounting not only for leg dynamics but also for modeling errors and unknown dynamics mismatch in hardware and during contact. Additionally, learning the model with variable-frequency allows us to cover the entire flight phase and final jumping target, enhancing the prediction accuracy of the jumping trajectory. Using the learned model, we also design variable-frequency to effectively leverage different jumping phases and track the target accurately. In a total of 92 jumps on Unitree A1 robot hardware, we verify that our approach outperforms other MPCs using fixed frequency or nominal model, reducing the jumping distance error 2 to 8 times. We also achieve jumping distance errors of less than 3 percent during continuous jumping on uneven terrain with randomly placed perturbations of random heights (up to 4 cm or 27 percent the robot standing height). Our approach obtains distance errors of 1 to 2 cm on 34 single and continuous jumps with different jumping targets and model uncertainties. Code is available at https://github.com/DRCL-USC/Learning MPC Jumping.

cs.RO↗

arXiv2024

Mastering Agile Jumping Skills from Simple Practices with Iterative Learning Control

Achieving precise target jumping with legged robots poses a significant challenge due to the long flight phase and the uncertainties inherent in contact dynamics and hardware. Forcefully attempting these agile motions on hardware could result in severe failures and potential damage. Motivated by these challenging problems, we propose an Iterative Learning Control (ILC) approach that aims to learn and refine jumping skills from easy to difficult, instead of directly learning these challenging tasks. We verify that learning from simplicity can enhance safety and target jumping accuracy over trials. Compared to other ILC approaches for legged locomotion, our method can tackle the problem of a long flight phase where control input is not available. In addition, our approach allows the robot to apply what it learns from a simple jumping task to accomplish more challenging tasks within a few trials directly in hardware, instead of learning from scratch. We validate the method via extensive experiments in the A1 model and hardware for various jumping tasks. Starting from a small jump (e.g., a forward leap of 40cm), our learning approach empowers the robot to accomplish a variety of challenging targets, including jumping onto a 20cm high box, jumping to a greater distance of up to 60cm, as well as performing jumps while carrying an unknown payload of 2kg. Our framework can allow the robot to reach the desired position and orientation targets with approximate errors of 1cm and 1 degree within a few trials.

cs.RO↗

arXiv2024

SOAF: Scene Occlusion-aware Neural Acoustic Field

This paper tackles the problem of novel view audio-visual synthesis along an arbitrary trajectory in an indoor scene, given the audio-video recordings from other known trajectories of the scene. Existing methods often overlook the effect of room geometry, particularly wall occlusions on sound propagation, making them less accurate in multi-room environments. In this work, we propose a new approach called Scene Occlusion-aware Acoustic Field (SOAF) for accurate sound generation. Our approach derives a global prior for the sound field using distance-aware parametric sound-propagation modeling and then transforms it based on the scene structure learned from the input video. We extract features from the local acoustic field centered at the receiver using a Fibonacci Sphere to generate binaural audio for novel views with a direction-aware attention mechanism. Extensive experiments on the real dataset RWAVS and the synthetic dataset SoundSpaces demonstrate that our method outperforms previous state-of-the-art techniques in audio generation.

cs.CV↗

arXiv2024

HashPoint: Accelerated Point Searching and Sampling for Neural Rendering

In this paper, we address the problem of efficient point searching and sampling for volume neural rendering. Within this realm, two typical approaches are employed: rasterization and ray tracing. The rasterization-based methods enable real-time rendering at the cost of increased memory and lower fidelity. In contrast, the ray-tracing-based methods yield superior quality but demand longer rendering time. We solve this problem by our HashPoint method combining these two strategies, leveraging rasterization for efficient point searching and sampling, and ray marching for rendering. Our method optimizes point searching by rasterizing points within the camera's view, organizing them in a hash table, and facilitating rapid searches. Notably, we accelerate the rendering process by adaptive sampling on the primary surface encountered by the ray. Our approach yields substantial speed-up for a range of state-of-the-art ray-tracing-based methods, maintaining equivalent or superior accuracy across synthetic and real test datasets. The code will be available at https://jiahao-ma.github.io/hashpoint/.

cs.CV↗

arXiv2024

Homography Guided Temporal Fusion for Road Line and Marking Segmentation

Reliable segmentation of road lines and markings is critical to autonomous driving. Our work is motivated by the observations that road lines and markings are (1) frequently occluded in the presence of moving vehicles, shadow, and glare and (2) highly structured with low intra-class shape variance and overall high appearance consistency. To solve these issues, we propose a Homography Guided Fusion (HomoFusion) module to exploit temporally-adjacent video frames for complementary cues facilitating the correct classification of the partially occluded road lines or markings. To reduce computational complexity, a novel surface normal estimator is proposed to establish spatial correspondences between the sampled frames, allowing the HomoFusion module to perform a pixel-to-pixel attention mechanism in updating the representation of the occluded road lines or markings. Experiments on ApolloScape, a large-scale lane mark segmentation dataset, and ApolloScape Night with artificial simulated night-time road conditions, demonstrate that our method outperforms other existing SOTA lane mark segmentation models with less than 9\% of their parameters and computational complexity. We show that exploiting available camera intrinsic data and ground plane assumption for cross-frame correspondence can lead to a light-weight network with significantly improved performances in speed and accuracy. We also prove the versatility of our HomoFusion approach by applying it to the problem of water puddle segmentation and achieving SOTA performance.

cs.CV↗

arXiv2024

Syn3DWound: A Synthetic Dataset for 3D Wound Bed Analysis

Wound management poses a significant challenge, particularly for bedridden patients and the elderly. Accurate diagnostic and healing monitoring can significantly benefit from modern image analysis, providing accurate and precise measurements of wounds. Despite several existing techniques, the shortage of expansive and diverse training datasets remains a significant obstacle to constructing machine learning-based frameworks. This paper introduces Syn3DWound, an open-source dataset of high-fidelity simulated wounds with 2D and 3D annotations. We propose baseline methods and a benchmarking framework for automated 3D morphometry analysis and 2D/3D wound segmentation.

cs.CV↗

arXiv2023

Robust Quadruped Jumping via Deep Reinforcement Learning

In this paper, we consider a general task of jumping varying distances and heights for a quadrupedal robot in noisy environments, such as off of uneven terrain and with variable robot dynamics parameters. To accurately jump in such conditions, we propose a framework using deep reinforcement learning that leverages and augments the complex solution of nonlinear trajectory optimization for quadrupedal jumping. While the standalone optimization limits jumping to take-off from flat ground and requires accurate assumptions of robot dynamics, our proposed approach improves the robustness to allow jumping off of significantly uneven terrain with variable robot dynamical parameters and environmental conditions. Compared with walking and running, the realization of aggressive jumping on hardware necessitates accounting for the motors' torque-speed relationship as well as the robot's total power limits. By incorporating these constraints into our learning framework, we successfully deploy our policy sim-to-real without further tuning, fully exploiting the available onboard power supply and motors. We demonstrate robustness to environment noise of foot disturbances of up to 6 cm in height, or 33% of the robot's nominal standing height, while jumping 2x the body length in distance.

cs.RO↗

arXiv2023

Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container

In this paper, we define a new problem of recovering the 3D geometry of an object confined in a transparent enclosure. We also propose a novel method for solving this challenging problem. Transparent enclosures pose challenges of multiple light reflections and refractions at the interface between different propagation media e.g. air or glass. These multiple reflections and refractions cause serious image distortions which invalidate the single viewpoint assumption. Hence the 3D geometry of such objects cannot be reliably reconstructed using existing methods, such as traditional structure from motion or modern neural reconstruction methods. We solve this problem by explicitly modeling the scene as two distinct sub-spaces, inside and outside the transparent enclosure. We use an existing neural reconstruction method (NeuS) that implicitly represents the geometry and appearance of the inner subspace. In order to account for complex light interactions, we develop a hybrid rendering strategy that combines volume rendering with ray tracing. We then recover the underlying geometry and appearance of the model by minimizing the difference between the real and hybrid rendered images. We evaluate our method on both synthetic and real data. Experiment results show that our method outperforms the state-of-the-art (SOTA) methods. Codes and data will be available at https://github.com/hirotong/ReNeuS

cs.CV↗