Schedule

 

 8/1
Friday
(Online)

8/3
Sunday
 
 8/4
Monday
 8/5
Tuesday
 8/6
Wednesday

 09:00

      Oral 3
(좌장: 오태현 교수/KAIST)

 9:00 - 10:00

Mentoring
(Work & Life)


 9:00 - 10:00 

 
 09:30

      
Opening

 9:30 - 10:00 
 
  
 10:00

    Oral 1
(좌장: 김현우 교수/KAIST)

 10:00 - 11:00
Oral 4
(좌장: 이승용 교수/POSTECH)

 10:00 - 11:00
Oral 6
(좌장: 윤국진 교수/KAIST)

 10:00 - 11:00
 
 10:30
 
 Workshop 1
 10:30 - 12:00
 
 
11:00
 
 
Keynote 1Shree NayarColumbia University(좌장: 박인규 교수/인하대)
 11:00 - 12:00
 
Keynote 2Michal IraniWeizmann Institute of Science(좌장: 심현정 교수/KAIST)
 
 11:00 - 12:00 
Oral 7(좌장: 임성훈 교수/DGIST)
 11:00 - 12:00 
  
 11:30

 
  
 12:00

Lunch(Not provided)
 12:00 - 13:30 
  Lunch(Not provided)
 12:00 - 13:30  
Lunch(Not provided)
 12:00 - 13:30  
Lunch(Not provided)
 12:00 - 13:30 
  
 12:30

 
  
 13:00

 
  
 13:30

Tutorial 1
 13:30 - 14:45
  Oral 2
(좌장:박종일 교수/햔양대)

 13:30 - 14:30
Oral 5
(좌장: 서용덕 교수/서강대)

 13:30 - 14:30 
Oral 8
(좌장: 최종현 교수/서울대)

 13:30 - 14:30 
  
 14:00

 
  
 14:30

  Industry 1(좌장: 김원준 교수/건국대)
 14:30 - 15:30 
Industry 2(좌장: 한보형 교수/서울대)
 14:30 - 15:30 
Poster 3
 14:30 - 16:00 
 
 15:00
 
Tutorial 2
 15:00 - 16:15
 
  
 15:30

  Poster 1
 15:30 - 17:00
 Poster 2
 15:30 - 17:00 
  
 16:00

KCCV
프로그램 위원회


 16:00 - 17:00
 
Keynote 3Gul VarolÉcole des Ponts ParisTech(좌장: 심현정 교수/KAIST)
 16:00 - 17:00 
  
 16:30

 Tutorial 3
 16:30 - 17:45
 KCVS 이사회
(장소: 320호)
 16:30 - 15:30 
  
 17:00


DoctoralColloquium
 17:00 - 18:30
KCVS 총회
 17:00 - 18:00 

Close Remark
 17:00 - 17:30 

  
 17:30

  
 
 18:00
 
        

* Registration / Exhibition (8/4~8/6 10:00 - 18:00) 

8월 1일(금)
Workshop & Tutorial

Workshop.1
10:30 ~ 11:00
산업계에서의 인공지능 연구

김승욱
(NVIDIA)

Workshop.2
11:00 ~ 11:30
 진리의 파편을 찾아서

김승룡(KAIST)

Workshop.3 11:30 ~ 12:00
논문 수와 인용 수, 그 다음은?

오성준
(Univ. of
Tubingen)

Tutorial.113:30 ~ 15:00
Identity-preserving Distillation Sampling by Fixed-Point Iterator (CVPR 2025)
/Dual Recursive Feedback on Generation and Appearance Latents for Pose-Robust Text-to-Image Diffusion (ICCV 2025)
 
진경환
(고려대)

 Tutorial.215:00 ~ 16:30
Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining (ICLR 2025)
 
임성훈
(DGIST)

 Tutorial.316:30 ~ 17:45 
Pseudo-RIS: Distinctive Pseudo-Supervision Generation for Referring Image Segmentation (ECCV 2024)
 
손진희
(GIST)




8월 4일(월)
Oral Session 1 & Keynote 1

O1.1 10:00 ~ 10:20  EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting  김상필(고려대)
O1.210:20 ~ 10:40Latent space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models  김선주(연세대)
O1.310:40 ~ 11:00  A Simple yet Universal Framework for Depth Completion  전해곤(GIST)
Keynote 111:00 ~ 12:00 Computational Imaging and Future Cameras


Shree Nayar(Columbia University)

 

 

 


 

8월 4일(월)
Oral Session 2 & Industry Session 1

O2.1 13:30 ~ 13:50 MASH-VLM: Mitigating Action-Scene Hallucination in Video-LLMs through Disentangled Spatial-Temporal Representations  최진우(경희대)
O2.213:50 ~ 14:10Neural cover selection for steganography  김혜지(University of Texas at Austin)
O2.314:10 ~ 14:30 Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks 윤국진(KAIST)
I1.114:30 ~ 14:50 TBD
DeltaX
I1.214:50 ~ 15:10 TBD 
Lunit Inc.

I1.315:10 ~ 15:30 TBD 
Nexdata

 

 

 

8월 4일(월)
Poster Session 1


Poster No.

 

Time

Paper Name

Advisor

Presenter

1

15:30 ~ 17:00

GRAE-3DMOT: Geometry Relation-Aware Encoder for Online 3D Multi-Object Tracking

고영준

김현섭

2

Classification Matters: Improving Video Action Detection with Class-Specific Attention

곽수하

이진성

3

Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval

곽수하

정보승 

4

Towards Generalizable Scene Change Detection

 김의환

김재우

5

VideoMamba: Spatio-Temporal Selective State Space Model

김창익

김희선

6

REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning

 김창익

이지현 

7

Diffusion Prior-Based Amortized Variational Inference for Noisy Inverse Problems

 김현우

이소진

8

Deblurring 3D Gaussian Splatting

박은병

이병현

9

Event Ellipsometer: Event-based Mueller-Matrix Video Imaging

백승환

문윤성

10

BAM-DETR: Boundary-Aligned Moment Detection Transformer for Temporal Sentence Grounding in Videos

변혜란

이필현

11

Random Conditioning for Diffusion Model Compression with Distillation

서홍석

박세환

12

SyncTweedies: A General Generative Framework Based on Synchronized Diffusions

성민혁

여경민

13

Bootstrap Your Own Views: Masked Ego-Exo Modeling for Fine-grained View-invariant Video Representations

손광훈

박정인

14

Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather

심현정

박준성

15

Nearly Zero-Cost Protection Against Mimicry by Personalized Diffusion Models

안남혁

안남혁

16

TCFG: Tangential Damping Classifier-free Guidance

어영정

어영정

17

Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration

오태현

김준성

18

Do Your Best and Get Enough Rest for Continual Learning

유종빈

강한결

19

Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks

윤국진

양훈민

20

WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels

윤국진

권혁준

21

OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for OmOmnidirectional Images with Editable Capabilities

이경무

이수영

22

RAD: Region-Aware Diffusion Models for Image Inpainting

이민식

김소라

23

Style-Editor: Text-driven object-centric style editing

임성훈

박지훈

24

6DoF Head Pose Estimation through Explicit Bidirectional Interaction with Face Geometry

창주용

전성호

25

A Simple yet Universal Framework for Depth Completion

전해곤

박진휘

26

Continuous Locomotive Crowd Behavior Generation

전해곤

배인환

27

Black Hole-Driven Identity Absorbing in Diffusion Models

정순기

사허야르 무하마드

28

Probabilistic Weather Forecasting with Deterministic Guidance-based Diffusion Model

조동현

조동현

29

Video Summarization with Large Language Models

조민수

이민정

30

Leveraging 3D Geometric Priors in 2D Rotation Symmetry Detection

조민수

서아현

31

Towards Lossless Implicit Neural Representation via Bit Plane Decomposition

진경환

한우경

32

Identity-preserving Distillation Sampling by Fixed-Point Iterator

진경환

김선화

33

FIFO-Diffusion: Generating Infinite Videos from Text without Training

한보형

강준오

34

Subnet-Aware Dynamic Supernet Training for Neural Architecture Search

함범섭

전제민

35

Temporal Alignment-Free Video Matching for Few-shot Action Recognition

허재필

이수빈

36

Question-Aware Gaussian Experts for Audio-Visual Question Answering

홍성은

김홍엽

37

Your Large Vision-Language Model Only Needs A Few Attention Heads For Visual Grounding

황성재

강세일

38

Cross-View Completion Models are Zero-shot Correspondence Estimators

김승룡

안홍규




8월 4일(월)
Doctoral Colloquium

Doctoral
Colloquium
 17:00 ~ 18:00
TBD



8월 5일(화)
Oral Session 3

O3.19:00 ~ 9:20 A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection 배승환(인하대)
O3.29:20 ~ 9:40GOAL: Global-local Object Alignment Learning  엄찬호(중앙대)
O3.39:40 ~ 10:00 Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction 박은병(연세대)



8월 5일(화)
Oral Session 4 & Keynote 2

O4.110:00 ~ 10:20RGBD GS-ICP SLAM
유현우(성균관대)
O4.210:20 ~ 10:40Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild 홍승훈(KAIST)
O4.310:40 ~ 11:00Learning Audio-guided Video Representation with Gated Attention for Video-Text Retrieval 곽수하(POSTECH)
Keynote 211:00 ~ 12:00 Reading Minds & Machines 
Michal Irani(Weizmann Institute of Science)



8월 5일(화)
Oral Session 5 & Industry Session 2

O5.113:30 ~ 13:50 Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models 주한별(서울대)
O5.213:50 ~ 14:10 Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior 손진희(GIST)
O5.314:10 ~ 14:30NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model  장형진(University of Birmingham)
I2.114:30 ~ 14:50 TBD POSCO DX
I2.214:50 ~ 15:10 TBD
 Qualcomm

I2.315:10 ~ 15:30 TBD 
SK magic

 

 

 

8월 5일(화)
Poster Session 2

Poster No.

 

Time

Paper Name

Advisor

Presenter

1

15:30 ~ 17:00

 Efficient Neural Video Representation with Temporally Coherent Modulation

오도관

신승준

2

 Improving Sound Source Localization with Joint Slot Attention on Image and Audio

곽수하

김인호

3

 Bootstrapping Top-down Information for Self-modulating Slot Attention

곽수하

김동원

4

 Online Temporal Action Localization with Memory-Augmented Transformer

곽수하

송영길

5

 LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection

김동석

김산민

6

 VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness

김동진

차승주

7

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

김문철

서원용

8

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

김문철

박종민

9

 Enhanced Motion Forecasting with Visual Relation Reasoning

김상필

백하닮

10

 Latent space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models

김선주

정진호

11

ControlFace: Harnessing Facial Parametric Control for Face Rigging 

김승룡

양진이

12

 DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation

김영빈

권준형

13

 DropGaussian: Structural Regularization for Sparse-view Gaussian Splatting

김원준

박현우

14

 MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection

김정욱

정준영

15

Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation 

김창익

함석일

16

 Expressive Whole-Body 3D Gaussian Avatar

문경식

문경식

17

TADFormer : Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning 

민동보

백승민

18

SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting 

박은병

유지상

19

Link to the Past: Temporal Propagation for Fast 3D Human Reconstruction from Monocular Video 

박인규

Matthew Marchellus

20

 A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection

배승환

배승환

21

 GrounDiT: Grounding Diffusion Transformers via Noisy Patch Transplantation

성민혁

이유승

22

 Fine-Grained Image-Text Correspondence with Cost Aggregation for Open-Vocabulary Part Segmentation

심현정

최지호

23

 Memory-Efficient Fine-Tuning for Quantized Diffusion Model

심현정

임서현

24

 Optical-Flow Guided Prompt Optimization for Coherent Video Generation

예종철

김제민

25

 Dense-SfM: Structure from Motion with Dense Consistent Matching

유승주

유승주

26

 Multi-modal Knowledge Distillation-based Human Trajectory Forecasting

윤국진

정재우

27

TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight 

윤국진

김지훈

28

 NL2Contact: Natural Language Guided 3D Hand-Object Contact Modeling with Diffusion Model

장형진

장형진

29

PersonaBooth: Personalized Text-to-Motion Generation 

김보은

김보은

30

 Fully Explicit Dynamic Gaussian Splatting

전해곤

이준오

31

 Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation

조민수

이준하

32

Mask2Map: Vectorized HD Map Construction Using Bird's Eye View Segmentation Masks 

최준원

김정호

33

 DEVIAS: Learning Disentangled Video Representations of Action and Scene

최진우

안지오

34

 Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding

한보형

최진영

35

Auto-Encoded Supervision for Perceptual Image Super-Resolution 

허재필

이민규

36

 HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts

윤상두

윤상두

37

Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning

이준태, 윤성락

미정



 

8월 6일(수)
Oral Session 6 & Oral Session 7

O6.110:00 ~ 10:20 LC-Mamba: Local and Continuous Mamba with Shifted Windows for Frame Interpolation 이채은(한양대)
O6.210:20 ~ 10:40 DynScene: Scalable Generation of Dynamic Robotic Manipulation Scenes for Embodied AI 김희원(숭실대)

O6.310:40 ~ 11:00Bi-directional Contextual Attention for 3D Dense Captioning  김건희(서울대)

O7.111:00 ~ 11:20 TADFormer: Task-Adaptive Dynamic TransFormer for Efficient Multi-Task Learning 민동보(이화여대)
O7.211:20 ~ 11:40Identity-preserving Distillation Sampling by Fixed-Point Iterator  차은주(숙명여대)

O7.311:40 ~ 12:00BF-STVSR: B-Splines and Fourier—Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution  유재준(UNIST)




8월 6일(수)
Oral Session 8

O8.113:30 ~ 13:50 Random Conditioning for Diffusion Model Compression with Distillation 서홍석(고려대)
O8.213:50 ~ 14:10 Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation 조민수(POSTECH)

O8.314:10 ~ 14:30Model Stock: All we need is just a few fine-tuned models 
윤상두(NAVER)

 

 

  

8월 6일(수)
Poster Session 3


Poster No.

 

Time

Paper Name

Advisor

Presenter

1

14:30 ~ 16:00

ContactField: Implicit Field Representation for Multi-Person Interaction Geometry

임화섭

유택근 

2

Seurat: From Moving Points to Depth

이준영 

신희성 

3

Embedding-Free Transformer with Inference Spatial Reduction for Efficient Semantic Segmentation

 강석주

유현우 

4

 Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation

 Feng Yang

오경록 

5

 Decomposition of Neural Discrete Representations for Large-Scale 3D Mapping

 김은태

박민성 

6

VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions

 김진규

문석하 

7

 DynScene: Scalable Generation of Dynamic Robotic Manipulation Scenes for Embodied AI

 김희원

이상민, 박성용 

8

 SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing

 노준용

홍석현 

9

 ESC: Erasing Space Concept for Knowledge Deletion

 박경문, 황효석

이태영 

10

 ShowMak3r: Compositional TV Show Reconstruction

 박재식

김상민 

11

 Narrating the Video: Boosting Text-Video Retrieval via Comprehensive Utilization of Frame-Level Captions

 박상효, 박혜영

허찬 

12

 Pixel-aligned RGB-NIR Stereo Imaging and Dataset for Robot Vision

 백승환

김진녕 

13

 Towards Certifiably Robust Face Recognition

 서재홍

백승훈 

14

 VideoHandles: Editing 3D Object Compositions in Videos Using Video Generative Priors

 성민혁

구주일 

15

 Learning Representation for Multitask Learning Through Self-supervised Auxiliary Learning

 손영두

신석원 

16

 Data-free Universal Adversarial Perturbation with Pseudo-semantic Prior

 손진희

이찬희 

17

 Two is Better than One: an Efficient Ensemble Defense for Robust and Compact Model

 송병철

정유진 

18

 No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation

심현정 

박준성 

19

 GOAL: Global-local Object Alignment Learning

 엄찬호

최현규 

20

 Minority-Focused Text-to-Image Generation via Prompt Optimization

 예종철

음수빈 

21

 BF-STVSR: B-Splines and Fourier—Best Friends for High Fidelity Spatial-Temporal Video Super-Resolution

 유재준, 진경환

김현진 

22

 Syn-to-Real Domain Adaptation for Point Cloud Completion via Part-based Approach

 윤국진

김지훈 

23

 On-the-fly Category Discovery for LiDAR Semantic Segmentation

 윤국진

김현성 

24

Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation 

 윤상호

정한석 

25

 GeoAvatar: Geometrically-Consistent Multi-Person Avatar Reconstruction from Sparse Multi-View Videos

 이주호

이주호 

26

 Blind Image Deblurring with Noise-Robust Kernel Estimation

 장무석

이찬석 

27

 Is 'Right' Right? Enhancing Object Orientation Understanding in Multimodal Large Language Models through Egocentric Instruction Tuning

 장부루, 김범수

김은태 

28

 Kinetic Typography Diffusion Model

전해곤 

박선미 

29

Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection 

정재훈 

송동수 

30

Locality-Aware Interaction for Zero-Shot Human-Object Interaction Detection 

 조민수

김상현 

31

 Dynamic Pseudo Labeling via Gradient Cutting for High-Low Entropy Exploration

 조성인

전주현 

32

 HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics

 주경돈

이종성 

33

 ReALFRED: An Embodied Instruction Following Benchmark in Photo-Realistic Environments

 최종현

김병휘 

34

 Resilient Sensor Fusion under Adverse Sensor Failures via Multi-Modal Expert Fusion

 최준원

박건율 

35

 Integration of Global and Local Representations for Fine-grained Cross-modal Alignment

 한경식

진승완 

36

 Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations

 황상흠

김정현 

37

 I2-SLAM: Inverting Imaging Process for Robust Photorealistic Dense SLAM

 김영민

배광탁 

38

 Model Stock: All We Need Is Just a Few Fine-Tuned Models

 윤상두, 한동윤

한동윤 




8월 6일(수)
Keynote 3

Keynote 316:00 ~ 17:00 TBD Gul Varol(Ecole des Ponts ParisTech)

8월 10일(화)
Oral Session B

O2b.1 13:20 ~ 13:40 Position-based Scaled Gradient for Model Compression 곽노준
(서울대)
[실시간생중계]
O2b.2 13:40 ~ 14:00 Rapid Neural Architecture Search with Meta-Learning 황성주
(KAIST)
O2b.3 14:00 ~ 14:20 Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentation 심현정
(연세대)
O2b.4 14:20 ~ 14:40 Few-shot Open-set Recognition 김창익
(KAIST)
O2b.5 14:40 ~ 15:00 Realizing AI: Two Insights from Field Experiences 유동근
(Lunit)

8월 10일(화)
Oral Session C

O2c.1 16:30 ~ 16:50 GATSBI: Generative Agent-centric Spatio-temporal Object Interaction 김영민
(서울대)
[실시간생중계]
O2c.2 16:50 ~ 17:10 Single Image Defocus Deblurring 이승용
(POSTECH)
O2c.3 17:10 ~ 17:30 Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing 어영정
(연세대)

8월 11일(수)
Oral Session A & Invited Talk

Invited Talk 3 10:00 ~ 11:00 First-Person Video for Understanding Interactions Kristen Grauman
(UT Austin)
[실시간생중계]
O3a.1 11:00 ~ 11:20 Task-Aware Quantization Network for JPEG Image Compression 한보형
(서울대)
O3a.2 11:20 ~ 11:40 Network Quantization with Element-wise Gradient Scaling 함범섭
(연세대)
O3a.3 11:40 ~ 12:00 Deep Learning-based Pupil Center Detection for Fast and Accurate Eye Tracking System 송병철
(인하대)

8월 11일(수)
Oral Session B

O3b.1 13:20 ~ 13:40 Self-supervised Learning for Videos 김건희
(서울대)
[실시간생중계]
O3b.2 13:40 ~ 14:00 Restore from Restored: Image and Video Restoration 김태현
(한양대)
O3b.3 14:00 ~ 14:20 Events to End-task Learning for Computer Vision 윤국진
(KAIST)
O3b.4 14:20 ~ 14:40 FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation 황원준
(아주대)
O3b.5 14:40 ~ 15:00 How Critical Are Localization and Perception Technologies for Enhanced Autonomous Driving? 김덕훈
(Qualcomm)

8월 11일(수)
Doctoral Colloquium

Doctoral Colloquium 16:30 ~ 17:30 김장호(서울대), 손형석(POSTECH), 김형준(POSTECH), 왕린(KAIST) [실시간생중계]