Schedule

 

 8/1
Friday

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

 09:00

       Oral 3

■ 9:00 - 10:00

 Mentoring
(Work & Life)

■ 9:00 - 10:00 

 
 09:30

      
Opening
■ 9:30 - 10:00 

  
 10:00

     Oral 1
■ 10:00 - 11:00		 Oral 4
■ 10:00 - 11:00		 Oral 6
■ 10:00 - 11:00
 
 10:30
 		  Workshop 1
■ 10:30 - 12:00		  
 
11:00
 		  
Keynote 1Shree Nayar(Columbia University)
■ 11:00 - 12:00
 		 Keynote 2Michal Irani(Weizmann Institute of Science)
■ 11:00 - 12:00 		 Oral 7
■ 11:00 - 12:00 
  
 11:30

  
  
 12:00

 Lunch
■ 12:00 - 13:30 		   Lunch
■ 12:00 - 13:30  		 Lunch
■ 12:00 - 13:30  		 Lunch
■ 12:00 - 13:30 
  
 12:30

  
  
 13:00

  
  
 13:30

 Tutorial 1
■ 13:30 - 14:45		   Oral 2
■ 13:30 - 14:30		 Oral 5
■ 13:30 - 14:30 		 Oral 8
■ 13:30 - 14:30 
  
 14:00

  
  
 14:30

   Industry 1
■ 14:30 - 15:30 		 Industry 2
■ 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 Varol(École des Ponts ParisTech)
■ 16:00 - 17:00   
  
 16:30

  Tutorial 3
■ 16:30 - 17:45
  
 17:00

  KCVS 이사회

■ 17:00 - 18:00		 DoctoralColloquium
■ 17:00 - 18:00		 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

Worshop.1
10:30 ~ 11:00
TBD

김승욱(NVIDIA)

Worshop.2
11:00 ~ 11:30
 TBD

김승룡(KAIST)

Worshop.3 11:30 ~ 12:00
TBD

오성준
(Univ. of
Tubingen)

Tutorial.113:30 ~ 15:00
TBD
 
TBD

 Tutorial.215:00 ~ 16:30
TBD
 
TBD

 Tutorial.316:30 ~ 17:45 
TBD
 
TBD




8월 4일(월)
Oral Session 1 & Keynote 1

O1.110:00 ~ 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 ~ 10:40
 
 Latent space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models


김선주(연세대)
 O1.310:40 ~ 11:00 Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
윤국진(KAIST)
 Keynote 111:00 ~ 12:00TBD
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 A Simple yet Universal Framework for Depth Completion 전해곤(GIST)
I1.114:30 ~ 14:50 TBD
DeltaX
I1.214:50 ~ 15:10 TBD 
Lunit

I1.315:10 ~ 15:30 TBD 
Ainextdata

 


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 TBD 
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 poscoDX
I2.214:50 ~ 15:10 TBD
 Qualcomm

I2.315:10 ~ 15:30 TBD 
SKmagic





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 ~ 14:30 TBD 
TBD



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]