CMLab@CAU - Publications

Preprints / Under Review (*: equal contribution, †: corresponding author)

🫠 DiTTo: Scalable Order-aware All-in-One Image Restoration Agent

Seungho Choi, and Jihyong Oh†

[arXiv2026][Project Page]

🦎 Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing

Sukhun Ko, Soo Ye Kim† and Jihyong Oh†

[arXiv2026][Project Page]

🪄 RefGC-SR²: Reference-guided Super-Resolution and Refinement of AI Generated Content

Jeahun Sung*, Dahyeon Kye*, Soo Ye Kim† and Jihyong Oh†

[Project_Page]

🦦 SEAL : Semantic-aware Single-image Sticker Personalization with a Large-scale Sticker-tag Dataset

Changhyun Roh, Yonghyun Jeong, Jonghyun Lee, Chanho Eom† and Jihyong Oh†

[arXiv2026][Project Page]

🏆 SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting

Seokhyun Youn*, Soohyun Lee*, Geonho Kim*, Weeyoung Kwon, Sung-Ho Bae† and Jihyong Oh†

[arXiv2025][Project Page][Awesome-Efficient-GS]

🦁 CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metric

Dahyeon Kye*, Jeahun Sung*, Minkyu Jeon, and Jihyong Oh†

[arXiv2025][Project Page]

🇰🇷 COREA: Coupled Relightable 3D Gaussians and SDFs for Efficient Normal Alignment

Jaeyoon Lee*, Hojoon Jung*, Seongtae Hwang, Jihyong Oh†, and Jongwon Choi†

[arXiv2025][Project Page]

✏️ Training-free Style Control and Style Fidelity Metric for Text-Image Manipulation

Agus Gunawan, Soo Ye Kim, Jihyong Oh†, and Munchurl Kim†

[coming soon]

🔎 AVSR-Diff: Scale-Agnostic Diffusion Priors for Temporally Consistent Arbitrary-Scale Video Super-Resolution

Geunhyuk Youk, Jeonghyeok Do, Dayeon Kim, Jihyong Oh†, and Munchurl Kim†

[coming soon]

֎ FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring

Geunhyuk Youk, Jihyong Oh†, and Munchurl Kim†

[arXiv2025][Project Page]

🏃🏻 MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer

Samuel Teodoro, Yun Chen, Agus Gunawan, Soo Ye Kim, Jihyong Oh†, and Munchurl Kim†

[arXiv2026][Project Page]

🧊 R3eVision: A Survey on Robust Rendering, Restoration, and Enhancement for 3D Low-Level Vision

Weeyoung Kwon, Jeahun Sung, Minkyu Jeon, Chanho Eom, and Jihyong Oh†

[arXiv2025][Awesome-3D-Low-Level-Vision]

🎯 PRIMEdit: Probability Redistribution for Instance-aware Multi-object Video Editing with Benchmark Dataset

Samuel Teodoro*, Agus Gunawan*, Soo Ye Kim, Jihyong Oh†, and Munchurl Kim†

[arXiv2025][Project Page]

International Publications (*: equal contribution, †: corresponding author, C: conference, J: journal)

Our lab has published multiple papers in top-tier AI/CV venues including CVPR, ICCV, ECCV, ICLR, and AAAI.

Our publications include:

• 8 papers at CVPR (including 1 Oral, 2 Highlight)

• 3 papers at ICCV (1 Highlight, 2 Oral)

• additional papers at ECCV, ICLR, and AAAI.

In addition, our work has appeared in leading journals such as IEEE TPAMI, IEEE TCSVT, and Neurocomputing.

CMLab 🖥️ GitHub: [link]

[J7]🂡 AceVFI: A Comprehensive Survey of Advances in Video Frame Interpolation

Dahyeon Kye, Changhyun Roh, Sukhun Ko, Chanho Eom, and Jihyong Oh†

IEEE TCSVT (IF=11.1)

Early Access (DOI: 10.1109/TCSVT.2026.3672288)

[arXiv2025][IEEE TCSVT][Awesome-Video-Frame-Interpolation]

[C17] 🚂 MoRel: Long-Range Flicker-Free 4D Motion Modeling via Anchor Relay-based Bidirectioanl Blending with Hierarchical Densification

Sangwoon Kwak*, Weeyoung Kwon*, Jun Young Jeong, Geonho Kim, Won-Sik Cheong, and Jihyong Oh†

CVPR 2026 (🏅Highlight Paper Rate: 3.6% ≈ 578/16,092)

Collab.w/ETRI[arXiv2025][Project Page][GitHub][CVPR2026]

[C16]🖼️ FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution

Seungho Choi, Jeahun Sung, and Jihyong Oh†

CVPR 2026 (Acceptance Rate: 25.42% ≈ 4,090/16,092)

[arXiv2025][Project Page][GitHub][CVPR2026]

[C15]🌱 EcoSplat: Efficiency-controllable Feed-forward 3D Gaussian Splatting from Multi-view Images

Jongmin Park*, Minh-Quan Viet Bui*, Juan Luis Gonzalez, Jaeho Moon, Jihyong Oh†, and Munchurl Kim†

CVPR 2026 (🏅Highlight Paper Rate: 3.6% ≈ 578/16,092)

Collab.w/KAIST[arXiv2025][Project Page][GitHub][CVPR2026]

[C14]✨ FLAIR: Frequency- and Locality-Aware Implicit Neural Representations

Sukhun Ko, SeokHyun Youn, Dahyeon Kye, Kyle Min, Chanho Eom, and Jihyong Oh†

CVPR 2026 (Findings) (Acceptance Rate: 36.1% ≈ (4,090+1,717)/16,092)

Collab.w/Oracle[arXiv2025][Project Page][GitHub][CVPRF2026]

[C13]🖌 OmniText: A Training-Free Generalist for Controllable Text-Image Manipulation

Agus Gunawan*, Samuel Teodoro*, Yun Chen, Soo Ye Kim, Jihyong Oh†, and Munchurl Kim†

ICLR 2026 (Acceptance Rate: 28% ≈ 5,320/19,000)

Collab.w/AdobeResearch,KAIST[ICLR2026][arXiv2025][Project Page][GitHub]

[J6]☕️ MoCHA-former: Moiré-Conditioned Hybrid Adaptive Transformer for Video Demoiréing

Jeahun Sung, Changhyun Roh, Chanho Eom, and Jihyong Oh†

Neurocomputing (IF=6.5)

vol. 669, 132477, March 07, 2026 (DOI: https://doi.org/10.1016/j.neucom.2025.132477)

[Neurocomputing][Project Page][GitHub]

[C12]🕵🏻‍♂️ MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video

Minh-Quan Viet Bui*, Jongmin Park*, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh†, and Munchurl Kim†

AAAI 2026 (Acceptance Rate: 17.6% ≈ 4,167/23,680)

Collab.w/FlawlessAI,KAIST[arXiv2025][Project Page][GitHub][AAAI2026]

[C11]♻️ I-INR: Iterative Implicit Neural Representations

Ali Haider*, Muhammad Salman Ali*, Maryam Qamar, Tahir Khalil, Soo Ye Kim, Jihyong Oh†, Enzo Tartaglione, and Sung-Ho Bae†

AAAI 2026 (Acceptance Rate: 17.6% ≈ 4,167/23,680)

Collab.w/AdobeResearch,TélécomParis,KyungheeUniv.[arXiv2025][AAAI2026]

[J5]🌀 SoFoNO: Arbitrary-Scale Image Super-Resolution via Sobolev Fourier Neural Operator

Jong Kwon Oh*, Hwijae Son*, Hyung Ju Hwang, and Jihyong Oh†

Neurocomputing (IF=6.5)

vol. 661, 14 January 2026, 131944 (DOI: https://doi.org/10.1016/j.neucom.2025.131944)

Collab.w/POSTECH,KonkukUniv.[Neurocomputing][Project Page][GitHub]

[C10]🔍 DiffPS: Leveraging Prior Knowledge of Diffusion Model for Person Search

Giyeol Kim*, Sooyoung Yang*, Jihyong Oh, Myungjoo Kang, and Chanho Eom†

ICCV 2025 (🏅Highlight Paper Rate: 2.35% ≈ 263/11,152)

Collab.w/SeoulNationalUniv.[ICCV2025][Project Page][GitHub]

[J4]MoBluRF 🫨: Motion Deblurring Neural Radiance Fields for Blurry Monocular Video

Minh-Quan Viet Bui*, Jongmin Park*, Jihyong Oh†, and Munchurl Kim†

IEEE TPAMI (IF=18.6)

vol. 47, issue 9, pp. 7752-7770, Sep. 2025 (DOI: 10.1109/TPAMI.2025.3574644)

Collab.w/KAIST[IEEE TPAMI][Project Page][Note: previous ver.: DyBluRF 🫨][GitHub]

[J3]Domain Generalization for Person Re-identification 🫆: A Survey Towards Domain-Agnostic Person Matching

Hyunseo Lee, Juhyun Park, Jihyong Oh, and Chanho Eom†

Neurocomputing (IF=6.5)

vol. 649, no. 10, pp. 130763-130782, Oct. 07, 2025 (DOI: https://doi.org/10.1016/j.neucom.2025.130763)

[Neurocomputing][Awesome-Domain-Generalizable-Person-Re-identification]

[C9]∿ SplineGS: Robust Motion-Adaptive Spline for Real-Time Dynamic 3D Gaussians from Monocular Video

Jongmin Park*, Minh-Quan Viet Bui*, Juan Luis Gonzalez Bello, Jaeho Moon, Jihyong Oh†, and Munchurl Kim†

CVPR 2025 (Acceptance Rate: 22.1% ≈ 2,878/13,008)

Collab.w/KAIST[arXiv2024][Project Page][GitHub]

[C8]MoDec🎄-GS: Global-to-Local Motion Decomposition and Temporal Interval Adjustment for Compact Dynamic 3D Gaussian Splatting

Sangwoon Kwak, Joonsoo Kim, Jun Young Jeong, Won-Sik Cheong, Jihyong Oh†, and Munchurl Kim†

CVPR 2025 (Acceptance Rate: 22.1% ≈ 2,878/13,008)

Collab.w/ETRI,KAIST[arXiv2025][Project Page][GitHub]

[C7]⏱️ BiM-VFI: Bidirectional Motion Field-Guided Frame Interpolation for Video with Non-uniform Motions

Wonyong Seo, Jihyong Oh†, and Munchurl Kim†

CVPR 2025 (Acceptance Rate: 22.1% ≈ 2,878/13,008)

Collab.w/KAIST[arXiv2024][Project Page][GitHub]

[C6]🍎 FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring

Geunhyuk Youk, Jihyong Oh†, and Munchurl Kim†

CVPR 2024 (🏅Oral Paper Rate: 0.78% ≈ 90/11532, Acceptance Rate: 23.6% ≈ 2,719/11,532)

Collab.w/KAIST[arXiv2024][Project Page][GitHub][Demo][Video6mins]

[C5]DeMFI: Deep Joint Deblurring and Multi-Frame Interpolation with Flow-Guided Attentive Correlation and Recursive Boosting

Jihyong Oh and Munchurl Kim†

ECCV 2022 (Acceptance Rate: 28% ≈ 1,650/5,803 )

[ECCV2022][Supp][GitHub][Demo][Poster][Video5mins]

[C4]XVFI: eXtreme Video Frame Interpolation

Hyeonjun Sim*, Jihyong Oh*, and Munchurl Kim†

ICCV 2021 (🏅Oral Paper Rate: 3%, Acceptance Rate: 25.9% ≈ 1,617/6,236)

[arXiv][ICCV2021][Supp][GitHub][X4K1000FPS][Demo][Oral12mins] [Flowframes(GUI)][Poster]

[J2]PeaceGAN: A GAN-based Multi-Task Learning Method for SAR Target Image Generation with a Pose Estimator and an Auxiliary Classifier

Jihyong Oh and Munchurl Kim†

Remote Sensing (IF=5.0)

vol. 13, issue 19: 3939, Oct. 2021 (DOI: https://doi.org/10.3390/rs13193939)

[Remote Sensing]

[J1]SPAM-Net: A CNN-based SAR Target Recognition Network with Pose Angle Marginalization Learning

Jihyong Oh*, Gwang-Young Youm*, and Munchurl Kim†

IEEE TCSVT (IF=8.4)

vol. 31, issue 2, pp. 701-714, Feb. 2021. (DOI: 10.1109/TCSVT.2020.2987346)

[Paper][IEEE TCSVT]

[C3]FISR: Deep Joint Frame Interpolation and Super-Resolution with a Multi-Scale Temporal Loss

Soo Ye Kim*, Jihyong Oh*, and Munchurl Kim†

AAAI 2020 (Acceptance Rate: 20.6% ≈ 1,591/7,737 )

[Paper][GitHub][Poster][Spotlight-PPT]

[C2]JSI-GAN: GAN-Based Joint Super-Resolution and Inverse Tone-Mapping with Pixel-Wise Task-Specific Filters for UHD HDR Video

Soo Ye Kim*, Jihyong Oh*, and Munchurl Kim†

AAAI 2020 (Acceptance Rate: 20.6% ≈ 1,591/7,737 )

[Paper][GitHub][Poster][Spotlight-PPT]

[C1] Deep SR-ITM: Joint Learning of Super-Resolution and Inverse Tone-Mapping for 4K UHD HDR Applications

Soo Ye Kim, Jihyong Oh, and Munchurl Kim†

ICCV 2019 (🏅Oral Paper Rate: 4 %, Acceptance Rate: 25% ≈ 1,077/4,303)

[Paper][GitHub][Poster][Oral-PPT]

Selected Domestic and Regional Publications

[R12]Jeongho Seo, Weeyoung Kwon, Seokhyun Youn, Seungho Choi and Jihyong Oh†, "테스트 타임 최적화를 활용한 동적 장면 블러 제거를 위한 FFN 기반 4D 재구성 연구", Summer Annual Conference of IEIE (2026년도 대한전자공학회 하계학술대회), 2026.
[R11]Seokhyun Youn and Jihyong Oh†, "GausPart: Part-wise Material Property Assignment to 3D Gaussians via MLLM", ITC-CSCC, 2026.
[R10]Sukhun Ko, Chanho Eom, and Jihyong Oh†, "Implicit Neural Representations: A Holistic Survey of Techniques, Applications, and Challenges", IEIE SPC, 2026.
[R9]Jeahun Sung and Jihyong Oh†, "MC-Former: Moiré-Content Decoupling for Spatio-Temporal Transformers in RAW Video Demoiréing", ICEIC, 2026. [Special Session: Non-IEEE Publication Track]
[R8]Dahyeon Kye and Jihyong Oh†,"이중 DDIM 인버전 기반 제로샷 이미지 모핑 기법 연구", Autumn Annual Conference of IEIE, 2025 (대한전자공학회 2025년도 추계학술대회). [link]
[R7]Weeyoung Kwon and Jihyong Oh†, "Toward Real-World 3D Rendering", 방송과 미디어 제30권 제3호, 2025. [link]
[R6]Dahyeon Kye*, Jaeho Choi*, Sukhun Ko, Weeyoung Kwon, Changhyun Roh, Jaehun Sung, Heeyoung Cho†, and Jihyong Oh†, "AI-Based Short-Form Animation Generation Utilizing Greek Mythological Hero’s Journey", Summer Annual Conference of IEIE (2025년도 대한전자공학회 하계학술대회 논문집), 2025. [link]
[R5]Hyunseo Lee, Changhyun Roh, Jihyong Oh, and Chanho Eom†, "Enhancing Motion Fluidity and Visual Consistency in Film Production with AI Generative Models", Moving Image and Technology (MINT), Vol. 5, No. 3, December 2025. [link]
[R4]Dahyeon Kye, Jeahun Sung, Chanho Eom, and Jihyong Oh†, “Evaluation of Generative Models for Mosaic Media Art", Moving Image & Technology (MINT), 2024. [link]
[R3]Jeahun Sung, Chanho Eom, and Jihyong Oh†, “State of the Art on Demoiréing Models", Journal of Arts and Imaging Science (TechArt), 2025. [link]
[R2]Jihyong Oh and Munchurl Kim†, “SAR Image Generation based on GAN with an Auxiliary Classifier", 2018 한국군사과학기술학회 (KIMST) 창립 20주년 종합학술대회.
[R1]Gwang-Young Youm, Jihyong Oh, and Munchurl Kim†, “A Deep Convolution Network for Fast SAR Automatic Target Detection and Recognition", 2018 한국군사과학기술학회 (KIMST) 창립 20주년 종합학술대회.

Patents (South Korea) (2023~)

[P9][2026.05.27] 출원번호: 10-2026-0095620, "참조 기반 AI 생성 콘텐츠 초해상화 및 정제 장치 및 방법 (Apparatus and Method for Reference-guided Super-Resolution and Refinement of AI-Generated Content)" [오지형, 계다현, 성제훈]
[P8][2026.05.27] 출원번호: 10-2026-0095621, "스타일-콘텐츠 분리 기반 교차 도메인 객체 합성 장치 및 방법 (Apparatus and Method for Cross-Domain Object Compositing Based on Style-Content Disentanglement)" [오지형, 고석훈]
[P7][2026.05.27] 출원번호: 10-2026-0095619, "복원 순서 인지 기반 다중 열화 이미지 복원 장치 및 방법 (Apparatus and Method for Multi-Degradation Image Restoration Based on Order-aware Restoration)" [오지형, 최승호]
[P6][2026.02.12] 출원번호: 10-2026-0028291, "소볼레프 푸리에 신경 연산자를 이용한 임의 배율 영상 초해상화 방법 및 장치 (Arbitrary-scale image super-resolution method and apparatus using a Sobolev Fourier neural operator)" [오지형, 황형주, 오종권, 손휘재]
[P5][2026.01.29] 출원번호: 10-2026-0018369, "이종 3차원 표현 간의 양방향 기하 감독 기반 단계적 정렬 방법 및 장치 (Method and Apparatus for Progressive Alignment Between Heterogeneous 3D Representations Using Bidirectional Geometric Supervision)" [오지형, 최종원, 정호준, 이재윤]
[P4][2026.01.29] 출원번호: 10-2026-0018370, "적응적 캐시 주입 및 시맨틱 앵커 프롬프트를 이용한 제로샷 이미지 모핑 장치 및 방법 (Zero-shot Image Morphing Apparatus and Method Using Adaptive Cache Injection and Semantic Anchor Prompting)" [오지형, 성제훈, 계다현]
[P3][2026.01.29] 출원번호: 10-2026-0018368, "주파수 정렬 자기 증류와 적응형 모듈레이션을 이용한 실세계 이미지 초해상도 학습 방법 및 장치 (Method and Apparatus for Real-World Image Super-Resolution Using Frequency-Aligned Self-Distillation and Adaptive Modulation)" [오지형, 최승호]
[P2][2025.09.25] 출원번호: 10-2025-0138709, "무아레 조건부 하이브리드 적응형 트랜스포머를 이용한 비디오 무아레 제거 방법 및 장치 (Moire-Conditioned Hybrid Adaptive Transformer for Video Demoireing method and device)" [오지형, 성제훈, 엄찬호]
[P1][2025.09.25] 출원번호: 10-2025-0138708, "주파수 및 지역성 인식 암묵적 신경 표현 방법 및 장치 (Frequency and locality-aware implicit neural representation method and device)" [오지형, 고석훈, 엄찬호]

Page updated

Google Sites

Report abuse