Computer Vision Lab

Decoupled Generative Modeling for Human-Object Interaction Synthesis
Hwanhee Jung, Seunggwan Lee, Jeongyoon Yoon, SeungHyeon Kim, Giljoo Nam, Qixing Huang, Sangpil Kim
Collaboration : META Realty Lab, University of Texas At Austin
#15
arXiv

ICP-4D: Bridging Iterative Closest Point and LiDAR Panoptic Segmentation
Gyeongrok Oh, Youngdong Jang, Jonghyun Choi, Suk-Ju Kang, Guang Lin, Sangpil Kim
Collaboration : Hyndai, Purdue University, Sogang University
#14
arXiv

M³KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation
Hyeongcheol Park, Jiyoung Seo, Jaewon Mun, Hogun Park, Wonmin Byeon, Sung June Kim, Hyeonsoo Im, JeungSub Lee, Sangpil Kim
Collaboration : Hanwha, NVIDIA Research, Sungkyunkwan University
#13
arXiv

WaTeRFlow: Watermark Temporal Robustness via Flow Consistency
Utae Jeong, Sumin In, Hyunju Ryu, Jaewan Choi, Feng Yang, Jongheon Jeong, Seungryong Kim, Sangpil Kim
Collaboration : Google DeepMind, KAIST
#12
arXiv

RevoNAD: Reflective Evolutionary Exploration for Neural Architecture Design
Gyusam Chang, Jeongyoon Yoon, Shin han yi, JaeHyeok Lee, Sujin Jang, Sangpil Kim
Collaboration : Samsung AI Center
#11
arXiv

HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Prediction
Jong Wook Kim, Wonseok Roh, Ha Dam Baek, Pilhyeon Lee, Jonghyun Choi, Sangpil Kim
Collaboration : Hyndai, Inha University
#10
arXiv

Dynamic-eDiTor: Training-Free Text-Driven 4D Scene Editing with Multimodal Diffusion Transformer
Dong In Lee, Hyungjun Doh, Seunggeun Chi, Runlin Duan, Sangpil Kim*, Karthik Ramani*
Collaboration : Purdue University
#9
arXiv

AgriChrono: A Multi-modal Dataset Capturing Crop Growth and Lighting Variability with a Field Robot
Jaehwan Jeong, Tuan-Anh Vu, Mohammad Jony, Shahab Ahmad, Mukhlesur Rahman, Sangpil Kim*, M. Khalid Jawed*
Collaboration : UCLA
#8
arXiv

ForgeSAM: Confidence-Aware Multi-Cue Representations for Robust Forgery Localization
Hanyi Shin, Hadam Baek, Namhyuk Ahn, Pilhyeon Lee, Euijin Choo, Sangpil Kim
Collaboration : Alberta University, Inha University
#7

Egocentric Hand Activity Video Dataset and Bidirectional Motion-Priors for Hand Action Recognition
Jiyoung Seo, Dong In Lee, Pilhyeon Lee, Jiwoo Lee, YounHee Gil, Karthik Ramani, Sangpil Kim
Collaboration : Purdue University, Inha University
#6

VAT-KG: Knowledge-Intensive Multimodal Knowledge Graph Dataset for Retrieval-Augmented Generation
Hyeongcheol Park, MinHyuk Jang, Ha Dam Baek, Gyusam Chang, Jiyoung Seo, Jiwan Park, Hogun Park, Sangpil Kim
Collaboration : Sungkyunkwan University
#5

CompMarkGS: Robust Watermarking for Compression 3D Gaussian Splatting
Sumin In, Youngdong Jang, Utae Jeong, MinHyuk Jang, Hyeongcheol Park, Eunbyung Park, Sangpil Kim
Collaboration : Younsei University
#4

AV-Surf: Surface-Enhanced Geometry-Aware Novel-View Acoustic Synthesis
Ha Dam Baek, Shin han yi, Jiyoung Seo, Chanwoo Kim, Saerom Kim, Hyeongbok Kim, Sangpil Kim
#3

LVMark: Robust Watermark for latent video diffusion models
MinHyuk Jang, Youngdong Jang, JaeHyeok Lee, Kodai Kawamura , Feng Yang, Sangpil Kim
Collaboration : Google DeepMind
arXiv
Collaboration : AIWORKS
#2