Kyong Hwan Jin
YOU?
Author Swipe
View article: TAG:Tangential Amplifying Guidance for Hallucination-Resistant Diffusion Sampling
TAG:Tangential Amplifying Guidance for Hallucination-Resistant Diffusion Sampling Open
Recent diffusion models achieve the state-of-the-art performance in image generation, but often suffer from semantic inconsistencies or hallucinations. While various inference-time guidance methods can enhance generation, they often operat…
View article: JPEG Processing Neural Operator for Backward-Compatible Coding
JPEG Processing Neural Operator for Backward-Compatible Coding Open
Despite significant advances in learning-based lossy compression algorithms, standardizing codecs remains a critical challenge. In this paper, we present the JPEG Processing Neural Operator (JPNeO), a next-generation JPEG algorithm that ma…
View article: Anti‐jamming thermoacoustic imaging based on fiber Bragg grating ultrasonic detection and photoelectric conversion triggering
Anti‐jamming thermoacoustic imaging based on fiber Bragg grating ultrasonic detection and photoelectric conversion triggering Open
Background Thermoacoustic Imaging (TAI) combines the high contrast of microwave imaging with the high resolution of ultrasound imaging, establishing itself as a novel, non‐invasive medical diagnostic technique. However, the high‐power (pea…
View article: Versatile Tunable Terahertz Absorption Device Based on Bulk Dirac Semimetals and Graphene
Versatile Tunable Terahertz Absorption Device Based on Bulk Dirac Semimetals and Graphene Open
We employed the CST Microwave Studio software 2020 and the FDID algorithm for simulation. We have designed a terahertz broadband absorber based on Dirac semimetals and graphene, achieving continuous broadband absorption with a rate exceedi…
View article: BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution
BF-STVSR: B-Splines and Fourier-Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution Open
While prior methods in Continuous Spatial-Temporal Video Super-Resolution (C-STVSR) employ Implicit Neural Representation (INR) for continuous encoding, they often struggle to capture the complexity of video data, relying on simple coordin…
View article: Tunable multiple narrowband polarization stable metamaterial terahertz absorbers based on dirac semi metal and phase change material VO2
Tunable multiple narrowband polarization stable metamaterial terahertz absorbers based on dirac semi metal and phase change material VO2 Open
In this work, we take advantage of the characteristic of bulk Dirac semimetals (BDS) that their Fermi level can be controlled by electrostatic doping, as well as the phase transition characteristics of vanadium dioxide (VO2). Combining the…
View article: A Noise is Worth Diffusion Guidance
A Noise is Worth Diffusion Guidance Open
Diffusion models excel in generating high-quality images. However, current diffusion models struggle to produce reliable images without guidance methods, such as classifier-free guidance (CFG). Are guidance methods truly necessary? Observi…
View article: BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow
BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow Open
Multi frame super-resolution(MFSR) achieves higher performance than single image super-resolution (SISR), because MFSR leverages abundant information from multiple frames. Recent MFSR approaches adapt the deformable convolution network (DC…
View article: JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients
JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients Open
We propose a practical approach to JPEG image decoding, utilizing a local implicit neural representation with continuous cosine formulation. The JPEG algorithm significantly quantizes discrete cosine transform (DCT) spectra to achieve a hi…
View article: Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance Open
Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as classifier guidance (CG) and classifier-free guidance (CFG). …
View article: Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings
Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings Open
Recording neuronal activity using multiple electrodes has been widely used to understand the functional mechanisms of the brain. Increasing the number of electrodes allows us to decode more variety of functionalities. However, handling mas…
View article: DeepFold: enhancing protein structure prediction through optimized loss functions, improved template features, and re-optimized energy function
DeepFold: enhancing protein structure prediction through optimized loss functions, improved template features, and re-optimized energy function Open
Motivation Predicting protein structures with high accuracy is a critical challenge for the broad community of life sciences and industry. Despite progress made by deep neural networks like AlphaFold2, there is a need for further improveme…
View article: Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings
Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings Open
Supplementary Data for "Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings", Hong et al.
View article: Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings
Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings Open
Supplementary Data for "Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings", Hong et al.
View article: BroadBEV: Collaborative LiDAR-camera Fusion for Broad-sighted Bird's Eye View Map Construction
BroadBEV: Collaborative LiDAR-camera Fusion for Broad-sighted Bird's Eye View Map Construction Open
A recent sensor fusion in a Bird's Eye View (BEV) space has shown its utility in various tasks such as 3D detection, map segmentation, etc. However, the approach struggles with inaccurate camera BEV estimation, and a perception of distant …
View article: Implicit Neural Image Stitching
Implicit Neural Image Stitching Open
Existing frameworks for image stitching often provide visually reasonable stitchings. However, they suffer from blurry artifacts and disparities in illumination, depth level, etc. Although the recent learning-based stitchings relax such di…
View article: Learning Residual Elastic Warps for Image Stitching under Dirichlet Boundary Condition
Learning Residual Elastic Warps for Image Stitching under Dirichlet Boundary Condition Open
Trendy suggestions for learning-based elastic warps enable the deep image stitchings to align images exposed to large parallax errors. Despite the remarkable alignments, the methods struggle with occasional holes or discontinuity between o…
View article: Learning Local Implicit Fourier Representation for Image Warping
Learning Local Implicit Fourier Representation for Image Warping Open
Image warping aims to reshape images defined on rectangular grids into arbitrary shapes. Recently, implicit neural functions have shown remarkable performances in representing images in a continuous manner. However, a standalone multi-laye…
View article: Local Texture Estimator for Implicit Representation Function
Local Texture Estimator for Implicit Representation Function Open
Recent works with an implicit neural function shed light on representing images in arbitrary resolution. However, a standalone multi-layer perceptron shows limited performance in learning high-frequency components. In this paper, we propos…
View article: Time-Dependent Deep Image Prior for Dynamic MRI
Time-Dependent Deep Image Prior for Dynamic MRI Open
We propose a novel unsupervised deep-learning-based algorithm for dynamic magnetic resonance imaging (MRI) reconstruction. Dynamic MRI requires rapid data acquisition for the study of moving organs such as the heart. Existing reconstructio…
View article: Reducing the Human Effort in Developing PET-CT Registration
Reducing the Human Effort in Developing PET-CT Registration Open
We aim to reduce the tedious nature of developing and evaluating methods for aligning PET-CT scans from multiple patient visits. Current methods for registration rely on correspondences that are created manually by medical experts with 3D …
View article: Self-Supervised Deep Active Accelerated MRI
Self-Supervised Deep Active Accelerated MRI Open
We propose to simultaneously learn to sample and reconstruct magnetic resonance images (MRI) to maximize the reconstruction quality given a limited sample budget, in a self-supervised setup. Unlike existing deep methods that focus only on …
View article: Direct Reconstruction of Saturated Samples in Band-Limited OFDM Signals
Direct Reconstruction of Saturated Samples in Band-Limited OFDM Signals Open
Given a set of samples, a few of them being possibly saturated, we propose an efficient algorithm in order to cancel saturation while reconstructing band-limited signals. Our method satisfies a minimum-loss constraint and relies on sinc-re…
View article: Unified Theory for Recovery of Sparse Signals in a General Transform Domain
Unified Theory for Recovery of Sparse Signals in a General Transform Domain Open
Compressed sensing is provided a data-acquisition paradigm for sparse signals. Remarkably, it has been shown that the practical algorithms provide robust recovery from noisy linear measurements acquired at a near optimal sampling rate. In …
View article: Grid-Free Localization Algorithm Using Low-Rank Hankel Matrix for Super-Resolution Microscopy
Grid-Free Localization Algorithm Using Low-Rank Hankel Matrix for Super-Resolution Microscopy Open
Localization microscopy, such as STORM / PALM, can reconstruct super-resolution images with a nanometer resolution through the iterative localization of fluorescence molecules. Recent studies in this area have focused mainly on the localiz…
View article: 3D BBPConvNet to reconstruct parallel MRI
3D BBPConvNet to reconstruct parallel MRI Open
In recent years, compressed sensing techniques have been applied to the reconstruction of parallel magnetic resonance (MR) images. Particularly for 3D MR signal, it is crucial to acquire fewer samples to reduce the distortions caused by lo…