arXiv subjects

Juhui Lee

Publications and source records attributed to Juhui Lee.

6 recordsLinked to original sources

arXiv2026

Robust Image Processing Techniques for Construction Environment Monitoring Using Underwater Robots

This paper proposes a robust image processing framework for underwater robot-based construction environment monitoring, targeting complex degradations observed in real marine environments. Unlike conventional approaches that mainly consider absorption and backscattering, real underwater imagery is strongly affected by depth-dependent forward scattering blur and particle-induced degradations such as marine snow. To address this, we introduce a staged processing pipeline that sequentially models background degradation via depth-aware forward scattering and foreground degradation using realistic marine snow patterns extracted from real images. The resulting synthetic data are used to retrain an existing Joint-ID network without modifying its architecture, enabling an isolated evaluation of dataset realism. In addition, a lightweight post-processing scheme is applied to enhance contrast and structural clarity. Experiments on real underwater datasets collected in Korean coastal environments demonstrate consistent improvements in visual quality and UIQM scores. The results indicate that explicitly modeling forward scattering and realistic particle effects effectively reduces the synthetic-to-real gap and improves practical applicability in real-world underwater robotic operations.

cs.CV↗

arXiv2026

GSAT: Geometric Traversability Estimation using Self-supervised Learning with Anomaly Detection for Diverse Terrains

Safe autonomous navigation requires reliable estimation of environmental traversability. Traditional methods have relied on semantic or geometry-based approaches with human-defined thresholds, but these methods often yield unreliable predictions due to the inherent subjectivity of human supervision. While self-supervised approaches enable robots to learn from their own experience, they still face a fundamental challenge: the positive-only learning problem. To address these limitations, recent studies have employed Positive-Unlabeled (PU) learning, where the core challenge is identifying positive samples without explicit negative supervision. In this work, we propose GSAT, which addresses these limitations by constructing a positive hypersphere in latent space to classify traversable regions through anomaly detection without requiring additional prototypes (e.g., unlabeled or negative). Furthermore, our approach employs joint learning of anomaly classification and traversability prediction to more efficiently utilize robot experience. We comprehensively evaluate the proposed framework through ablation studies, validation on heterogeneous real-world robotic platforms, and autonomous navigation demonstrations in simulation environments.

cs.RO↗

arXiv2026

KISS-IMU: Self-supervised Inertial Odometry with Motion-balanced Learning and Uncertainty-aware Inference

Inertial measurement units (IMUs), which provide high-frequency linear acceleration and angular velocity measurements, serve as fundamental sensing modalities in robotic systems. Recent advances in deep neural networks have led to remarkable progress in inertial odometry. However, the heavy reliance on ground truth data during training fundamentally limits scalability and generalization to unseen and diverse environments. We propose KISS-IMU, a novel self-supervised inertial odometry framework that eliminates ground truth dependency by leveraging simple LiDAR-based ICP registration and pose graph optimization as a supervisory signal. Our approach embodies two key principles: keeping the IMU stable through motion-aware balanced training and keeping the IMU strong through uncertainty-driven adaptive weighting during inference. To evaluate performance across diverse motion patterns and scenarios, we conducted comprehensive experiments on various real-world platforms, including quadruped robots. Importantly, we train only the IMU network in a self-supervised manner, with LiDAR serving solely as a lightweight supervisory signal rather than requiring additional learnable processes. This design enables the framework to ensure robustness without relying on joint multi-modal learning or ground truth supervision. The supplementary materials are available at https://sparolab.github.io/research/kiss_imu.

cs.RO↗

arXiv2010

Coherent-state optical qudit cluster state generation and teleportation via homodyne detection

Defining a computational basis of pseudo-number states, we interpret a coherent state of large amplitude, $|α|\gg\frac{d}{2π}$, as a qudit --- a $d$-level quantum system --- in a state that is an even superposition of $d$ pseudo-number states. A pair of such coherent-state qudits can be prepared in maximally entangled state by generalized Controlled-$Z$ operation that is based on cross-Kerr nonlinearity, which can be weak for large $d$. Hence, a coherent-state optical qudit cluster state can be prepared by repetitive application of the generalized Controlled-$Z$ operation to a set of coherent states. We thus propose an optical qudit teleportation as a simple demonstration of cluster state quantum computation.

quant-ph↗

arXiv2009

Demonstrating higher-order nonclassical effects by photon-added classical states: Realistic schemes

Detecting nonclassical properties that do not allow classical interpretation of photoelectric counting events is one of the crucial themes in quantum optics. Observation of individual nonclassical effects for a single-mode field, however, has been so far practically confined to sub-Poissonian statistics and quadrature squeezing. We show that a photon-added classical (coherent or thermal) state exhibits generalized nonclassical features in all orders of creation and annihilation operators, thereby becoming a promising candidate for studying higher-order nonclassical effects. Our analysis demonstrates robustness of these effects against nonideal experimental conditions.

quant-ph↗

arXiv2003

Entanglement swapping secures multiparty quantum communication

Extending the eavesdropping strategy devised by Zhang, Li and Guo [Phys. Rev. A 63, 036301 (2001)], we show that the multiparty quantum communication protocol based on entanglement swapping, which was proposed by Cabello [quant-ph/0009025], is not secure. We modify the protocol so that entanglement swapping can secure multiparty quantum communication, such as multiparty quantum key distribution and quantum secret sharing of classical information, and show that the modified protocol is secure against the Zhang-Li-Guo's strategy for eavesdropping as well as the basic intercept-resend attack.

quant-ph↗