arXiv subjects

Jongmin Park

Publications and source records attributed to Jongmin Park.

At least 19 recordsLinked to original sources

arXiv2026

WebSpline: Structure-Informed Splines for Real-Time 3D Gaussians from Monocular Videos

Dynamic scene reconstruction from monocular videos remains highly challenging, as existing methods often struggle to balance global structural coherence and local fine-grained details under limited multi-view cues. To address this challenge, we propose WebSpline, a novel dynamic 3D Gaussian framework that enables structurally coherent and high-fidelity reconstruction from monocular videos with fast rendering. The core of WebSpline is the Structure-Informed Spline (SIS) representation, which models each dynamic Gaussian trajectory using a learnable cubic Hermite spline whose motion is structurally organized with an auxiliary Structural Proxy Graph (SPG). The proposed framework is optimized in two stages: (i) in the first stage, the SPG is initialized from 2D point tracks and refined with temporal rigidity regularization to establish structural coherence for moving objects across the sequence; and (ii) in the second stage, the SIS representation is initialized from the refined SPG and optimized under both spatial and structural neighborhood constraints. At inference, Gaussian motion is obtained solely by evaluating the learned SIS, enabling fast rendering. Extensive experiments on the challenging monocular dynamic scene benchmarks, iPhone and NVIDIA, demonstrate that our WebSpline achieves state-of-the-art rendering quality while rendering over 10 times faster than WorldTree, the second-best method on the iPhone dataset.

cs.CV↗

arXiv2026

AA-Splat: Anti-Aliased Feed-forward Gaussian Splatting

Feed-forward 3D Gaussian Splatting (FF-3DGS) emerges as a fast and robust solution for sparse-view 3D reconstruction and novel view synthesis (NVS). However, existing FF-3DGS methods are built on incorrect screen-space dilation filters, causing severe rendering artifacts when rendering at out-of-distribution sampling rates. We firstly propose an FF-3DGS model, called AA-Splat, to enable robust anti-aliased rendering at any resolution. AA-Splat utilizes an opacity-balanced band-limiting (OBBL) design, which combines two components: a 3D band-limiting post-filter integrates multi-view maximal frequency bounds into the feed-forward reconstruction pipeline, effectively band-limiting the resulting 3D scene representations and eliminating degenerate Gaussians; an Opacity Balancing (OB) to seamlessly integrate all pixel-aligned Gaussian primitives into the rendering process, compensating for the increased overlap between expanded Gaussian primitives. AA-Splat demonstrates drastic improvements with average 5.4$\sim$7.5dB PSNR gains on NVS performance over a state-of-the-art (SOTA) baseline, DepthSplat, at all resolutions, between $4\times$ and $1/4\times$. Code will be made available.

cs.CV↗

arXiv2026

Hyperbolic Heterogeneous Graph Transformer

In heterogeneous graphs, we can observe complex structures such as tree-like or hierarchical structures. Recently, the hyperbolic space has been widely adopted in many studies to effectively learn these complex structures. Although these methods have demonstrated the advantages of the hyperbolic space in learning heterogeneous graphs, most existing methods still have several challenges. They rely heavily on tangent-space operations, which often lead to mapping distortions during frequent transitions. Moreover, their message-passing architectures mainly focus on local neighborhood information, making it difficult to capture global hierarchical structures and long-range dependencies between different types of nodes. To address these limitations, we propose Hyperbolic Heterogeneous Graph Transformer (HypHGT), which effectively and efficiently learns heterogeneous graph representations entirely within the hyperbolic space. Unlike previous message-passing based hyperbolic heterogeneous GNNs, HypHGT naturally captures both local and global dependencies through transformer-based architecture. Furthermore, the proposed relation-specific hyperbolic attention mechanism in HypHGT, which operates with linear time complexity, enables efficient computation while preserving the heterogeneous information across different relation types. This design allows HypHGT to effectively capture the complex structural properties and semantic information inherent in heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness and efficiency of HypHGT, and the results demonstrate that it consistently outperforms state-of-the-art methods in node classification task, with significantly reduced training time and memory usage.

cs.LG↗

arXiv2026

COMPASS: High-Efficiency Deep Image Compression with Arbitrary-scale Spatial Scalability

Recently, neural network (NN)-based image compression studies have actively been made and has shown impressive performance in comparison to traditional methods. However, most of the works have focused on non-scalable image compression (single-layer coding) while spatially scalable image compression has drawn less attention although it has many applications. In this paper, we propose a novel NN-based spatially scalable image compression method, called COMPASS, which supports arbitrary-scale spatial scalability. Our proposed COMPASS has a very flexible structure where the number of layers and their respective scale factors can be arbitrarily determined during inference. To reduce the spatial redundancy between adjacent layers for arbitrary scale factors, our COMPASS adopts an inter-layer arbitrary scale prediction method, called LIFF, based on implicit neural representation. We propose a combined RD loss function to effectively train multiple layers. Experimental results show that our COMPASS achieves BD-rate gain of -58.33% and -47.17% at maximum compared to SHVC and the state-of-the-art NN-based spatially scalable image compression method, respectively, for various combinations of scale factors. Our COMPASS also shows comparable or even better coding efficiency than the single-layer coding for various scale factors.

eess.IV↗

arXiv2025

EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images

Feed-forward 3D Gaussian Splatting (3DGS) enables efficient one-pass scene reconstruction, providing 3D representations for novel view synthesis without per-scene optimization. However, existing methods typically predict pixel-aligned primitives per-view, producing an excessive number of primitives in dense-view settings and offering no explicit control over the number of predicted Gaussians. To address this, we propose EcoSplat, the first efficiency-controllable feed-forward 3DGS framework that adaptively predicts the 3D representation for any given target primitive count at inference time. EcoSplat adopts a two-stage optimization process. The first stage is Pixel-aligned Gaussian Training (PGT) where our model learns initial primitive prediction. The second stage is Importance-aware Gaussian Finetuning (IGF) stage where our model learns rank primitives and adaptively adjust their parameters based on the target primitive count. Extensive experiments across multiple dense-view settings show that EcoSplat is robust and outperforms state-of-the-art methods under strict primitive-count constraints, making it well-suited for flexible downstream rendering tasks.

cs.CV↗

arXiv2025

MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video

We present MoBGS, a novel motion deblurring 3D Gaussian Splatting (3DGS) framework capable of reconstructing sharp and high-quality novel spatio-temporal views from blurry monocular videos in an end-to-end manner. Existing dynamic novel view synthesis (NVS) methods are highly sensitive to motion blur in casually captured videos, resulting in significant degradation of rendering quality. While recent approaches address motion-blurred inputs for NVS, they primarily focus on static scene reconstruction and lack dedicated motion modeling for dynamic objects. To overcome these limitations, our MoBGS introduces a novel Blur-adaptive Latent Camera Estimation (BLCE) method using a proposed Blur-adaptive Neural Ordinary Differential Equation (ODE) solver for effective latent camera trajectory estimation, improving global camera motion deblurring. In addition, we propose a Latent Camera-induced Exposure Estimation (LCEE) method to ensure consistent deblurring of both a global camera and local object motions. Extensive experiments on the Stereo Blur dataset and real-world blurry videos show that our MoBGS significantly outperforms the very recent methods, achieving state-of-the-art performance for dynamic NVS under motion blur.

cs.CV↗

arXiv2025

Correlation Analysis Between MF R-Mode Temporal ASF and Meteorological Factors

As the vulnerabilities of global navigation satellite systems (GNSS) have become more widely recognized, the need for complementary navigation systems has grown. Medium frequency ranging mode (MF R-Mode) has gained attention as an effective backup system during GNSS outages, owing to its strong signal strength and cost-effective scalability. However, to achieve accurate positioning, MF R-Mode requires correction for the additional secondary factor (ASF), a propagation delay affected by terrain. The temporal variation of ASF, known as temporal ASF, is typically corrected using reference stations; however, the effectiveness of this method decreases with distance from the reference station. In this study, we analyzed the correlation between temporal ASF and meteorological factors to evaluate the feasibility of predicting temporal ASF based on meteorological factors. Among these factors, temperature and humidity showed significant correlations with temporal ASF, suggesting their potential utility in ASF correction.

eess.SP↗

arXiv2025

Evaluating Particle Filtering for RSS-Based Target Localization under Varying Noise Levels and Sensor Geometries

Target localization is a critical task in various applications, such as search and rescue, surveillance, and wireless sensor networks. When a target emits a radio frequency (RF) signal, spatially distributed sensors can collect signal measurements to estimate the target's location. Among various measurement modalities, received signal strength (RSS) is particularly attractive due to its low cost, low power consumption, and ease of deployment. While particle filtering has previously been applied to RSS-based target localization, few studies have systematically analyzed its performance under varying sensor geometries and RSS noise levels. This paper addresses this gap by designing and evaluating a particle filtering algorithm for localizing a stationary target. The proposed method is compared with a conventional RSS-based trilateration approach across different sensor configurations and noise conditions. Simulation results indicate that particle filtering provides more accurate target localization than trilateration, particularly in scenarios with unfavorable sensor geometries and high RSS noise.

eess.SP↗

arXiv2025

Metapath-based Hyperbolic Contrastive Learning for Heterogeneous Graph Embedding

The hyperbolic space, characterized by a constant negative curvature and exponentially expanding space, aligns well with the structural properties of heterogeneous graphs. However, although heterogeneous graphs inherently possess diverse power-law structures, most hyperbolic heterogeneous graph embedding models rely on a single hyperbolic space. This approach may fail to effectively capture the diverse power-law structures within heterogeneous graphs. To address this limitation, we propose a Metapath-based Hyperbolic Contrastive Learning framework (MHCL), which uses multiple hyperbolic spaces to capture diverse complex structures within heterogeneous graphs. Specifically, by learning each hyperbolic space to describe the distribution of complex structures corresponding to each metapath, it is possible to capture semantic information effectively. Since metapath embeddings represent distinct semantic information, preserving their discriminability is important when aggregating them to obtain node representations. Therefore, we use a contrastive learning approach to optimize MHCL and improve the discriminability of metapath embeddings. In particular, our contrastive learning method minimizes the distance between embeddings of the same metapath and maximizes the distance between those of different metapaths in hyperbolic space, thereby improving the separability of metapath embeddings with distinct semantic information. We conduct comprehensive experiments to evaluate the effectiveness of MHCL. The experimental results demonstrate that MHCL outperforms state-of-the-art baselines in various graph machine learning tasks, effectively capturing the complex structures of heterogeneous graphs.

cs.LG↗

arXiv2025

Toward High Accuracy DME for Alternative Aircraft Positioning: SFOL Pulse Transmission in High-Power DME

The Stretched-FrOnt-Leg (SFOL) pulse is an advanced distance measuring equipment (DME) pulse that offers superior ranging accuracy compared to conventional Gaussian pulses. Successful SFOL pulse transmission has been recently demonstrated from a commercial Gaussian pulse-based DME in low-power mode utilizing digital predistortion (DPD) techniques for power amplifiers. These adjustments were achieved through software modifications, enabling SFOL integration without replacing existing DME infrastructure. However, the SFOL pulse is designed to optimize ranging capabilities by leveraging the effective radiated power (ERP) and pulse shape parameters permitted within DME specifications. Consequently, it operates with narrow margins against these specifications, potentially leading to non-compliance when transmitted in high-power mode. This paper introduces strategies to enable a Gaussian pulse-based DME to transmit the SFOL pulse while adhering to DME specifications in high-power mode. The proposed strategies involve use of a variant of the SFOL pulse and DPD techniques utilizing truncated singular value decomposition, tailored for high-power DME operations. Test results, conducted on a testbed utilizing a commercial Gaussian pulse-based DME, demonstrate the effectiveness of these strategies, ensuring compliance with DME specifications in high-power mode with minimal performance loss. This study enables cost-effective integration of high-accuracy SFOL pulses into existing high-power DME systems, enhancing aircraft positioning precision while ensuring compliance with industry standards.

eess.SP↗

arXiv2025

MoBluRF: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video

Neural Radiance Fields (NeRF), initially developed for static scenes, have inspired many video novel view synthesis techniques. However, the challenge for video view synthesis arises from motion blur, a consequence of object or camera movements during exposure, which hinders the precise synthesis of sharp spatio-temporal views. In response, we propose a novel motion deblurring NeRF framework for blurry monocular video, called MoBluRF, consisting of a Base Ray Initialization (BRI) stage and a Motion Decomposition-based Deblurring (MDD) stage. In the BRI stage, we coarsely reconstruct dynamic 3D scenes and jointly initialize the base rays which are further used to predict latent sharp rays, using the inaccurate camera pose information from the given blurry frames. In the MDD stage, we introduce a novel Incremental Latent Sharp-rays Prediction (ILSP) approach for the blurry monocular video frames by decomposing the latent sharp rays into global camera motion and local object motion components. We further propose two loss functions for effective geometry regularization and decomposition of static and dynamic scene components without any mask supervision. Experiments show that MoBluRF outperforms qualitatively and quantitatively the recent state-of-the-art methods with large margins.

cs.CV↗

arXiv2024

SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video

Synthesizing novel views from in-the-wild monocular videos is challenging due to scene dynamics and the lack of multi-view cues. To address this, we propose SplineGS, a COLMAP-free dynamic 3D Gaussian Splatting (3DGS) framework for high-quality reconstruction and fast rendering from monocular videos. At its core is a novel Motion-Adaptive Spline (MAS) method, which represents continuous dynamic 3D Gaussian trajectories using cubic Hermite splines with a small number of control points. For MAS, we introduce a Motion-Adaptive Control points Pruning (MACP) method to model the deformation of each dynamic 3D Gaussian across varying motions, progressively pruning control points while maintaining dynamic modeling integrity. Additionally, we present a joint optimization strategy for camera parameter estimation and 3D Gaussian attributes, leveraging photometric and geometric consistency. This eliminates the need for Structure-from-Motion preprocessing and enhances SplineGS's robustness in real-world conditions. Experiments show that SplineGS significantly outperforms state-of-the-art methods in novel view synthesis quality for dynamic scenes from monocular videos, achieving thousands times faster rendering speed.

cs.CV↗

arXiv2024

Multi-Hyperbolic Space-based Heterogeneous Graph Attention Network

To leverage the complex structures within heterogeneous graphs, recent studies on heterogeneous graph embedding use a hyperbolic space, characterized by a constant negative curvature and exponentially increasing space, which aligns with the structural properties of heterogeneous graphs. However, despite heterogeneous graphs inherently possessing diverse power-law structures, most hyperbolic heterogeneous graph embedding models use a single hyperbolic space for the entire heterogeneous graph, which may not effectively capture the diverse power-law structures within the heterogeneous graph. To address this limitation, we propose Multi-hyperbolic Space-based heterogeneous Graph Attention Network (MSGAT), which uses multiple hyperbolic spaces to effectively capture diverse power-law structures within heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness of MSGAT. The experimental results demonstrate that MSGAT outperforms state-of-the-art baselines in various graph machine learning tasks, effectively capturing the complex structures of heterogeneous graphs.

cs.LG↗

arXiv2024

Explicit Construction of Hermitian Yang-Mills Instantons on Coset Manifolds

In four dimensions, 't Hooft symbols offer a compact and powerful framework for describing the self-dual structures fundamental to instanton physics. Extending this to six dimensions, the six-dimensional 't Hooft symbols can be constructed using the isomorphism between the Lorentz group $Spin(6)$ and the unitary group $SU(4)$. We demonstrate that the six-dimensional self-dual structures governed by the Hermitian Yang-Mills equations can be elegantly organized using these generalized 't Hooft symbols. We also present a systematic method for constructing Hermitian Yang-Mills instantons from spin connections on six-dimensional manifolds using the generalized 't Hooft symbols. We provide a thorough analysis of the topological invariants such as instanton and Euler numbers.

hep-th↗

arXiv2024

Hyperbolic Heterogeneous Graph Attention Networks

Most previous heterogeneous graph embedding models represent elements in a heterogeneous graph as vector representations in a low-dimensional Euclidean space. However, because heterogeneous graphs inherently possess complex structures, such as hierarchical or power-law structures, distortions can occur when representing them in Euclidean space. To overcome this limitation, we propose Hyperbolic Heterogeneous Graph Attention Networks (HHGAT) that learn vector representations in hyperbolic spaces with meta-path instances. We conducted experiments on three real-world heterogeneous graph datasets, demonstrating that HHGAT outperforms state-of-the-art heterogeneous graph embedding models in node classification and clustering tasks.

cs.LG↗

arXiv2022

Accurate Open-set Recognition for Memory Workload

How can we accurately identify new memory workloads while classifying known memory workloads? Verifying DRAM (Dynamic Random Access Memory) using various workloads is an important task to guarantee the quality of DRAM. A crucial component in the process is open-set recognition which aims to detect new workloads not seen in the training phase. Despite its importance, however, existing open-set recognition methods are unsatisfactory in terms of accuracy since they fail to exploit the characteristics of workload sequences. In this paper, we propose Acorn, an accurate open-set recognition method capturing the characteristics of workload sequences. Acorn extracts two types of feature vectors to capture sequential patterns and spatial locality patterns in memory access. Acorn then uses the feature vectors to accurately classify a subsequence into one of the known classes or identify it as the unknown class. Experiments show that Acorn achieves state-of-the-art accuracy, giving up to 37% points higher unknown class detection accuracy while achieving comparable known class classification accuracy than existing methods.

cs.AI↗

arXiv2022

Indoor Path Planning for Multiple Unmanned Aerial Vehicles via Curriculum Learning

Multi-agent reinforcement learning was performed in this study for indoor path planning of two unmanned aerial vehicles (UAVs). Each UAV performed the task of moving as fast as possible from a randomly paired initial position to a goal position in an environment with obstacles. To minimize training time and prevent the damage of UAVs, learning was performed by simulation. Considering the non-stationary characteristics of the multi-agent environment wherein the optimal behavior varies based on the actions of other agents, the action of the other UAV was also included in the state space of each UAV. Curriculum learning was performed in two stages to increase learning efficiency. A goal rate of 89.0% was obtained compared with other learning strategies that obtained goal rates of 73.6% and 79.9%.

cs.RO↗

arXiv2022

Anatomy of Einstein Manifolds

An Einstein manifold in four dimensions has some configuration of $SU(2)_+$ Yang-Mills instantons and $SU(2)_-$ anti-instantons associated with it. This fact is based on the fundamental theorems that the four-dimensional Lorentz group $Spin(4)$ is a direct product of two groups $SU(2)_\pm$ and the vector space of two-forms decomposes into the space of self-dual and anti-self-dual two-forms. It explains why the four-dimensional spacetime is special for the stability of Einstein manifolds. We now consider whether such a stability of four-dimensional Einstein manifolds can be lifted to a five-dimensional Einstein manifold. The higher-dimensional embedding of four-manifolds from the viewpoint of gauge theory is similar to the grand unification of Standard Model since the group $SO(4) \cong Spin(4)/\mathbb{Z}_2 = SU(2)_+ \otimes SU(2)_-/\mathbb{Z}_2$ must be embedded into the simple group $SO(5) = Sp(2)/\mathbb{Z}_2$. Our group-theoretic approach reveals the anatomy of Riemannian manifolds quite similar to the quark model of hadrons in which two independent Yang-Mills instantons represent a substructure of Einstein manifolds.

hep-th↗