arXiv subjects

Jeonghyun Noh

Publications and source records attributed to Jeonghyun Noh.

4 recordsLinked to original sources

arXiv2026

Zero-shot CT Super-Resolution using Diffusion-based 2D Projection Priors and Signed 3D Gaussians

Computed tomography (CT) is important in clinical diagnosis, but acquiring high-resolution (HR) CT is constrained by radiation exposure risks. While deep learning-based super-resolution (SR) methods have shown promise for reconstructing HR CT from low-resolution (LR) inputs, supervised approaches require paired datasets that are often unavailable. Zero-shot methods address this limitation by operating on single LR inputs; however, they frequently fail to recover fine structural details due to limited LR information within individual volumes. To overcome these limitations, we propose a novel zero-shot 3D CT SR framework that integrates diffusion-based upsampled 2D projection priors into the 3D reconstruction process. Specifically, our framework consists of two stages: (1) LR CT projection SR, training a diffusion model on abundant X-ray data to upsample LR projections, thereby enhancing the scarce information inherent in the LR inputs. (2) 3D CT volume reconstruction, using 3D Gaussian splatting with our novel Negative Alpha Blending (NAB-GS), which models positive and negative Gaussian densities to learn signed residuals between diffusion-generated HR and upsampled LR projections. Our framework demonstrates superior quantitative and qualitative performance on two public datasets, and expert evaluations present the framework's clinical potential at 4x.

eess.IV↗

arXiv2025

Dual Interaction Network with Cross-Image Attention for Medical Image Segmentation

Medical image segmentation is a crucial method for assisting professionals in diagnosing various diseases through medical imaging. However, various factors such as noise, blurriness, and low contrast often hinder the accurate diagnosis of diseases. While numerous image enhancement techniques can mitigate these issues, they may also alter crucial information needed for accurate diagnosis in the original image. Conventional image fusion strategies, such as feature concatenation can address this challenge. However, they struggle to fully leverage the advantages of both original and enhanced images while suppressing the side effects of the enhancements. To overcome the problem, we propose a dual interactive fusion module (DIFM) that effectively exploits mutual complementary information from the original and enhanced images. DIFM employs cross-attention bidirectionally to simultaneously attend to corresponding spatial information across different images, subsequently refining the complementary features via global spatial attention. This interaction leverages low- to high-level features implicitly associated with diverse structural attributes like edges, blobs, and object shapes, resulting in enhanced features that embody important spatial characteristics. In addition, we introduce a multi-scale boundary loss based on gradient extraction to improve segmentation accuracy at object boundaries. Experimental results on the ACDC and Synapse datasets demonstrate the superiority of the proposed method quantitatively and qualitatively. Code available at: https://github.com/JJeong-Gari/DIN

cs.CV↗

arXiv2025

MC-INR: Efficient Encoding of Multivariate Scientific Simulation Data using Meta-Learning and Clustered Implicit Neural Representations

Implicit Neural Representations (INRs) are widely used to encode data as continuous functions, enabling the visualization of large-scale multivariate scientific simulation data with reduced memory usage. However, existing INR-based methods face three main limitations: (1) inflexible representation of complex structures, (2) primarily focusing on single-variable data, and (3) dependence on structured grids. Thus, their performance degrades when applied to complex real-world datasets. To address these limitations, we propose a novel neural network-based framework, MC-INR, which handles multivariate data on unstructured grids. It combines meta-learning and clustering to enable flexible encoding of complex structures. To further improve performance, we introduce a residual-based dynamic re-clustering mechanism that adaptively partitions clusters based on local error. We also propose a branched layer to leverage multivariate data through independent branches simultaneously. Experimental results demonstrate that MC-INR outperforms existing methods on scientific data encoding tasks.

cs.CV↗

arXiv2025

Synthetic Data Augmentation using Pre-trained Diffusion Models for Long-tailed Food Image Classification

Deep learning-based food image classification enables precise identification of food categories, further facilitating accurate nutritional analysis. However, real-world food images often show a skewed distribution, with some food types being more prevalent than others. This class imbalance can be problematic, causing models to favor the majority (head) classes with overall performance degradation for the less common (tail) classes. Recently, synthetic data augmentation using diffusion-based generative models has emerged as a promising solution to address this issue. By generating high-quality synthetic images, these models can help uniformize the data distribution, potentially improving classification performance. However, existing approaches face challenges: fine-tuning-based methods need a uniformly distributed dataset, while pre-trained model-based approaches often overlook inter-class separation in synthetic data. In this paper, we propose a two-stage synthetic data augmentation framework, leveraging pre-trained diffusion models for long-tailed food classification. We generate a reference set conditioned by a positive prompt on the generation target and then select a class that shares similar features with the generation target as a negative prompt. Subsequently, we generate a synthetic augmentation set using positive and negative prompt conditions by a combined sampling strategy that promotes intra-class diversity and inter-class separation. We demonstrate the efficacy of the proposed method on two long-tailed food benchmark datasets, achieving superior performance compared to previous works in terms of top-1 accuracy.

cs.CV↗