arXiv subjects

Joonkyu Park

Publications and source records attributed to Joonkyu Park.

7 recordsLinked to original sources

arXiv2026

Language-Assisted Super-Resolution from Real-World Low-Resolution Patches

Single image super-resolution aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs. Training SR models typically requires paired HR-LR data, which is difficult to obtain in reality. As a result, most methods synthesize LR images by artificially degrading HR images with handcrafted kernels or camera ISP adjustments. However, these synthetic degradations fail to capture the complexity of real LR images, leading to poor generalization in practice. To address this, we observe that even within a single high-quality image, regions at different depths exhibit varying resolutions, where distant regions act as LR patches and closer ones as HR patches. This allows the extraction of real, degradation-induced LR patches from real images. Since these LR patches lack paired HR counterparts, we propose LA-SR (Language Assistant for SR), a novel framework for unpaired SR. The key idea of LA-SR is to redefine unpaired SR in the language space, using vision-language models to bridge the LR-HR gap. LA-SR projects images into a semantically rich space representing both content and quality, and applies two language-guided losses: linguistic content loss to preserve semantic fidelity, and linguistic quality loss to enhance perceptual realism. With this alignment, LA-SR effectively super-resolves real LR inputs, producing realistic outputs that overcome the limitations of synthetic-data-trained methods.

cs.CV↗

arXiv2024

GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring

To train a deblurring network, an appropriate dataset with paired blurry and sharp images is essential. Existing datasets collect blurry images either synthetically by aggregating consecutive sharp frames or using sophisticated camera systems to capture real blur. However, these methods offer limited diversity in blur types (blur trajectories) or require extensive human effort to reconstruct large-scale datasets, failing to fully reflect real-world blur scenarios. To address this, we propose GS-Blur, a dataset of synthesized realistic blurry images created using a novel approach. To this end, we first reconstruct 3D scenes from multi-view images using 3D Gaussian Splatting (3DGS), then render blurry images by moving the camera view along the randomly generated motion trajectories. By adopting various camera trajectories in reconstructing our GS-Blur, our dataset contains realistic and diverse types of blur, offering a large-scale dataset that generalizes well to real-world blur. Using GS-Blur with various deblurring methods, we demonstrate its ability to generalize effectively compared to previous synthetic or real blur datasets, showing significant improvements in deblurring performance.

cs.CV↗

arXiv2022

Dynamic Tilting of Ferroelectric Domain Walls via Optically Induced Electronic Screening

Optical excitation perturbs the balance of phenomena selecting the tilt orientation of domain walls within ferroelectric thin films. The high carrier density induced in a low-strain BaTiO3 thin film by an above-bandgap ultrafast optical pulse changes the tilt angle that 90° a/c domain walls form with respect to the substrate-film interface. The dynamics of the changes are apparent in time-resolved synchrotron x-ray scattering studies of the domain diffuse scattering. Tilting occurs at 298 K, a temperature at which the a/b and a/c domain phases coexist but is absent at 343 K in the better ordered single-phase a/c regime. Phase coexistence at 298 K leads to increased domain-wall charge density, and thus a larger screening effect than in the single-phase regime. The screening mechanism points to new directions for the manipulation of nanoscale ferroelectricity.

cond-mat.mtrl-sci↗

arXiv2022

Recurrence-in-Recurrence Networks for Video Deblurring

State-of-the-art video deblurring methods often adopt recurrent neural networks to model the temporal dependency between the frames. While the hidden states play key role in delivering information to the next frame, abrupt motion blur tend to weaken the relevance in the neighbor frames. In this paper, we propose recurrence-in-recurrence network architecture to cope with the limitations of short-ranged memory. We employ additional recurrent units inside the RNN cell. First, we employ inner-recurrence module (IRM) to manage the long-ranged dependency in a sequence. IRM learns to keep track of the cell memory and provides complementary information to find the deblurred frames. Second, we adopt an attention-based temporal blending strategy to extract the necessary part of the information in the local neighborhood. The adpative temporal blending (ATB) can either attenuate or amplify the features by the spatial attention. Our extensive experimental results and analysis validate the effectiveness of IRM and ATB on various RNN architectures.

eess.IV↗

arXiv2020

Mesoscopic Elastic Distortions in GaAs Quantum Dot Heterostructures

Quantum devices formed in high-electron-mobility semiconductor heterostructures provide a route through which quantum mechanical effects can be exploited on length scales accessible to lithography and integrated electronics. The electrostatic definition of quantum dots in semiconductor heterostructure devices intrinsically involves the lithographic fabrication of intricate patterns of metallic electrodes. The formation of metal/semiconductor interfaces, growth processes associated with polycrystalline metallic layers, and differential thermal expansion produce elastic distortion in the active areas of quantum devices. Understanding and controlling these distortions presents a significant challenge in quantum device development. We report synchrotron x-ray nanodiffraction measurements combined with dynamical x-ray diffraction modeling that reveal lattice tilts with a depth-averaged value up to 0.04 deg. and strain on the order of 10^-4 in the two-dimensional electron gas (2DEG) in a GaAs/AlGaAs heterostructure. Elastic distortions in GaAs/AlGaAs heterostructures modify the potential energy landscape in the 2DEG due to the generation of a deformation potential and an electric field through the piezoelectric effect. The stress induced by metal electrodes directly impacts the ability to control the positions of the potential minima where quantum dots form and the coupling between neighboring quantum dots.

cond-mat.mes-hall↗

arXiv2019

Role of temperature-dependent electron trapping dynamics in the optically driven nanodomain transformation in a PbTiO${_3}$/SrTiO${_3}$ superlattice

The spontaneously formed striped polarization nanodomain configuration of a PbTiO${_3}$/SrTiO${_3}$ superlattice transforms to a uniform polarization state under above-bandgap illumination with a time dependence varying with the intensity of optical illumination and a well-defined threshold intensity. Recovery after the end of illumination occurs over a temperature-dependent period of tens of seconds at room temperature and shorter times at elevated temperatures. A model in which the screening of the depolarization field depends on the population of trapped electrons correctly predicts the observed temperature and optical intensity dependence.

cond-mat.mtrl-sci↗

arXiv2017

Photoinduced Domain Pattern Transformation in Ferroelectric/Dielectric Superlattices

The nanodomain pattern in ferroelectric/dielectric superlattices transforms to a uniform polarization state under above-bandgap optical excitation. X-ray scattering reveals a disappearance of domain diffuse scattering and an expansion of the lattice. The reappearance of the domain pattern occurs over a period of seconds at room temperature, suggesting a transformation mechanism in which charge carriers in long-lived trap states screen the depolarization field. A Landau-Ginzburg-Devonshire model predicts changes in lattice parameter and a critical carrier concentration for the transformation.

cond-mat.mtrl-sci↗