Seonghyeon Nam

Seoung Wug Oh

Younghyun Jo

Young Hwi Kim

Jaeyeon Kang

Miran Heo

Chang Ha Shin

Hyolim Kang

Suho Han

Dongyoung Kim

Subin Jeon

Sejong Yang

Hyungjun Noh

Sangheon Ahn

Minho Shim

Sungho Lee

Yunji Kim

Gunhee Nam

Kyungmin Kim

Yumin Ko

Sukjun Hwang

Jiwon Jung

Junhyeok Kim

Taehyun Kim

Hyunbo Shim

Dasol Lee

Hojin Joo

Minju Ki

Joungbin An

Yoonpyo Hong

Daekyu Kwon

Dongwoo Lee

Jaehyun Kang

Sangmin Han

Seungyeon Jung

Yunsu Park

Welcome to the Computational Intelligence & Photography Lab (CIP Lab) at the Department of Computer Science and Engineering, Pusan National University. Our lab is dedicated to advancing the fields of computational intelligence and digital photography through innovative research and development. We explore cutting-edge techniques in areas such as image processing, computer vision, machine learning, and deep learning, with a strong focus on their applications in photography and visual media. Our goal is to develop intelligent systems that can enhance various aspects of digital imaging, from image capture and enhancement to analysis and synthesis. We strive to contribute to both theoretical foundations and practical applications, fostering a dynamic research environment that encourages creativity and collaboration.

부산대학교 컴퓨터공학과 전산지능 및 사진 연구실 (CIP Lab)에 오신 것을 환영합니다. 저희 연구실은 혁신적인 연구 개발을 통해 전산 지능 및 디지털 사진 분야를 발전시키는 데 전념하고 있습니다. 이미지 처리, 컴퓨터 비전, 기계 학습 및 딥 러닝과 같은 분야의 최첨단 기술을 탐구하며, 사진 및 시각 미디어 응용 분야에 중점을 둡니다. 저희 목표는 이미지 캡처 및 향상부터 분석 및 합성에 이르기까지 디지털 이미징의 다양한 측면을 향상시킬 수 있는 지능형 시스템을 개발하는 것입니다. 이론적 기반과 실제 응용 모두에 기여하고 창의성과 협업을 장려하는 역동적인 연구 환경을 조성하기 위해 노력합니다.

Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation

Fast Video Object Segmentation by Reference-Guided Mask Propagation

Constructing image panoramas using dual-homography warping

EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images

A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising

Robust Radiometric Calibration and Vignetting Correction

A New In-Camera Imaging Model for Color Computer Vision and Its Application

Visual enhancement of old documents with hyperspectral imaging

Color Transfer Using Probabilistic Moving Least Squares

Text-Adaptive Generative Adversarial Networks: Manipulating Images with\n Natural Language

Approaching the computational color constancy as a classification problem through deep learning

Building Emotional Machines: Recognizing Image Emotions Through Deep Neural Networks

Nonlinear Camera Response Functions and Image Deblurring: Theoretical Analysis and Practice

Adult perspectives of learning musical instruments

Do It Yourself Hyperspectral Imaging with Everyday Digital Cameras

Video Object Segmentation Using Space-Time Memory Networks

Practical Single-Image Super-Resolution Using Look-Up Table

Investigating Loss Functions for Extreme Super-Resolution

Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language

Video Instance Segmentation using Inter-Frame Communication Transformers

Global Geometry Is Not Enough for Vision Representations

Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors

Learning Personalized Photographic Style from Pairwise User Preferences

Decomposed Attention Fusion in MLLMs for Training-Free Video Reasoning Segmentation

4D Scaffold Gaussian Splatting with Dynamic-Aware Anchor Growing for Efficient and High-Fidelity Dynamic Scene Reconstruction

UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations

Training-Free Acceleration of Video LLMs via Multi-Granular Spatio-Temporal Token Merging

CCMNet: Leveraging Calibrated Color Correction Matrices for Cross-Camera Color Constancy

Open-ended Hierarchical Streaming Video Understanding with Vision Language Models

Deep Learning for Image Super-Resolution: A Comprehensive Review

Generative Adversarial Networks for Realistic Image Synthesis

Efficient Image Denoising using Convolutional Neural Networks

Multi-modal Image Registration with Attention Mechanisms

Seon Joo Kim

Professor

In Cho

Ph.D. candidate

Woongoh Cho

Ph.D. Student

Jiwan Chung

Ph.D. Candidate

Jinwoo Kim

Jeongseok Hyun

Hanjung Kim

Minsu Kim

Jinho Jeong

Youngbeom Yoo

Jihyuk Byun

M.S. Student

In Sung Song

Jaeseong Lee

MS-PhD Student

Dongyun Kim

Mijin Yoo

Integrated M.S./Ph.D. Program Student

Yeeun Choi

Jiwoo Choi

Junhee Park

Junyoung Hong

Jinho Kim

Heechan Choi

Sooran Kim

Integrated M.S./Ph.D. Program student

Jeonghwan Cho

Integrated M.S./Ph.D. Student

Jaemin Kim

Undergraduate Intern

Jihye Yoo

Undergraduate Research Intern

Yena Kim

Jinho Jang

Jaeho Chae

Jiwoo Lee

Jun Hyeok Park

Chaeyoon Lim

Computational Intelligence & Photography Lab (CIPLAB)

교수님 소개

Seon Joo Kim

연구실 소개

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Global Geometry Is Not Enough for Vision Representations

Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors

Learning Personalized Photographic Style from Pairwise User Preferences

연구실 보유 특허

대학별 입시끈

우리 연구실 모집

교수님 소개

Seon Joo Kim

연구실 키워드

알럼나이가 간 회사

연구실 지원 방법

대우 조건

연도별 논문 인용수

저널 & 학회 논문 출판 수

연구실 논문 목록

Global Geometry Is Not Enough for Vision Representations

Unsupervised Monocular 3D Keypoint Discovery from Multi-View Diffusion Priors

Learning Personalized Photographic Style from Pairwise User Preferences

연구실 보유 특허

최근 3년간 연구실적 높은 연구실

대학별 입시끈

우리 연구실 모집