Computer Vision Lab

Reconstruction Using the Invisible: Intuition from NIR and Metadata for Enhanced 3D Gaussian Splatting
Gyusam Chang, Tuan-Anh Vu, Vivek Alumootil, Harris Song, Deanna Pham, Sangpil Kim*, M. Khalid Jawed*
Collaboration : UCLA
AAAI 2026
[Paper]
# 3D Vision # Gaussian Splatting

Test-Time Adaptation for Online Vision-Language Navigation with Feedback-based Reinforcement Learning
Sungjune Kim^†, Gyeongrok Oh^†, Heeju Ko, Daehyun Ji, Dongwook Lee, Byung-Jun Lee, Sujin Jang*, Sangpil Kim*
Collaboration : Samsung Advanced Institute of Technology
ICML 2025
[Paper]
# Physical AI # Vision-Language Navigation

3D-GSW: 3D Gaussian Splatting for Robust Watermarking
Youngdong Jang, Hyunje Park, Feng Yang, Heeju Ko, Euijin Choo,
Sangpil Kim*
Collaboration : Google DeepMind, Alberta University
CVPR 2025
[Paper] [Project] [Code]
# AI Safety # 3D Watermarking

Insightful Instance Features for 3D Instance Segmentation
Wonseok Roh, Hwanhee Jung, Giljoo Nam, , Dong In Lee, Hyeongcheol Park, Sang Ho Yoon, Jungseock Joo, Sangpil Kim*
Collaboration : META Reality Lab, UCLA, KAIST
CVPR 2025
[Paper] [Code]
# 3D Vision # 3D Instance Segmentation

3D Occupancy Prediction with Low-Resolution Queries via Prototype-aware View Transformation
Gyeongrok Oh^†, Sungjune Kim^†, Heeju Ko, Hyung-gun Chi, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sungjoon Choi, Sujin Jang*, Sangpil Kim*
Collaboration : Samsung Advanced Institute of Technology, Purdue University
CVPR 2025
[Paper] [Project]
# Autonomous Driving # Occupancy Prediction

Cropper: Vision-Language Model for Image Cropping through In-Context Learning
Seung Hyun Lee, Jijun jiang, Yiran Xu, Zhuofang Li, Junjie Ke, Yinxiao Li, Junfeng He, Steven Hickson, Katie Datsenko, Sangpil Kim, Ming-Hsuan Yang, Irfan Essa, Feng Yang*
Collaboration : Google Research, Georgia Tech University
CVPR 2025
[Paper]
# Multimodal Learning # Visual In-Context Learning

High-quality three-dimensional cartoon avatar reconstruction with Gaussian splatting
MinHyuk Jang, Jong Wook Kim, Youngdong Jang, Donghyun Kim, Wonseok Roh , InYong Hwang, Guang Lin, Sangpil Kim*
Collaboration : Hanhwa, Purdue University
Engineering Applications of Artificial Intelligence
(Elsevier, JCR IF Top 2.7%) 2025
[Paper] [Code]
# 3D Vision # Gaussian Splatting

Occlusion-Aware and Consistent Amodal Completion for 3D Human-Object Interaction Reconstruction
Hyungjun Doh^†, Dong In Lee^†, Seunggeun Chi, Pin-Hao Huang, Kwonjoon Lee, Sangpil Kim, Karthik Ramani*
Collaboration : Purdue University
ACM MultiMedia(MM) 2025
[Paper] [Project] [Code]
# 3D Vision # Human-Object Interaction

Prosthetic Keypoint Estimation for Alternative Exercise Recommendation in Lower Limb Disabilities
Taebeom Lee, Dongyoon Seo, Chiho Park, Sunghee Hong, and Sangpil Kim*
Human-centric Computing and Information Sciences(Springer, Q2) 2025
[Paper]
# Physical AI # Pose Estimation

Lightweight Test-time Adaptation for Robust Out-of-Distribution Face Recognition in Web Services
Dongyoon Seo, Taebeom Lee, Jeongyoon Yoon, Chiho Park , Sangpil Kim, Miyoung Kim, Byoungsoo Koh*
Journal of Web Engineering 2025
[Paper]
# Trustworthy AI # Robust Face Recognition

Perspective Crop Based Egocentric Hand Pose Estimation via Fisheye Stereo Vision
Hyejin Hur, Seongmin Beak, Younhee Gil, and Sangpil Kim*
Collaboration : ETRI
EuroGraphics(Poster) 2025
[Paper]
# Physical AI # Pose Estimation

Unified Domain Generalization and Adaptation for
Multi-View 3D Object Detection
Gyusam Chang, Jiwon Lee, Donghyun Kim, Jinkyu Kim, Dongwook Lee, Daehyun Ji, Sujin Jang*, Sangpil Kim*
Collaboration : Samsung Advanced Institute of Technology
NeurIPS 2024
[Paper] [Code]
# Autonomous Driving # Domain Adaptation

Posture-Informed Muscular Force Learning for
Robust Hand Pressure Estimation
Kyungjin Seo, Junghoon Seo, Hanseok Jeong, Sangpil Kim, Sang Ho Yoon*
Collaboration : KAIST
NeurIPS 2024
[Paper] [Project] [Code] [Data]
# Physical AI # Human-Object Interaction

FPANet: Frequency-based Video Demoireing using Frame-level Post Alignment
Gyeongrok Oh, Sungjune Kim, Heon Gu, Sang Ho Yoon, Jinkyu Kim*, Sangpil Kim*
Collaboration : LG Display, KAIST
Neural Networks(Elsevier, JCR IF Top 10%) 2024
[Paper] [Code]
# Signal Processing # Video Demoireing

Egocentric View Hand Action Recognition by Leveraging Hand Surface and Hand Grasp Type
Dong Yoon Seo, Hyunggun Chi, Sunghee Hong, Byoung Soo Koh, Karthik Ramani, Sangpil Kim*
Collaboration : Purdue University
ICPRAI 2024(Oral)
[Paper]
# Physical AI # Hand Action Recognition

MELA: Multi-Event Localization Answering Framework for Video Question Answering
Jimyeong Han, Sangpil Kim*, Hogun Park*
Collaboration : Sungkyunkwan University
ACM/SIGAPP Symposium On Applied Computing 2025
[Paper] [Code]
# Multimodal Learning # Video Question Answering

Bridging the Domain Gap by Clustering-based Image-Text Graph Matching
Daewon Chae Nokyung Park, Daewon Chae, Jeong Yong Shim, Sangpil Kim, Eun-Sol Kim*, Jinkyu Kim*
Collaboration : HanYang University
International Conference on Pattern Recognition (2024)
[Paper]
# Multimodal Learning # Vision-Language

Functional Hand Type Prior for 3D Hand Pose Estimation and Action Recognition from Egocentric View Monocular Videos
Wonseok Roh, Seung Hyun Lee, Wonjeong Ryoo, Gyeongrok Oh, Soo Yeon Hwang, Hyung-gun Chi, Sangpil Kim*
Collaboration : Purdue University
BMVC 2023 (Oral)
[Paper] [Code]
# Physical AI # Hand Pose Estimation

Event Fusion Photometric Stereo Network
Wonjeong Ryoo, Giljoo Nam, Jae-Sang Hyun*, Sangpil Kim*
Collaboration : Meta Reality Lab, Yonsei University
Neural Networks(Elsevier, JCR IF Top 10%) 2023
[Paper] [Project] [Code] [Dataset]
# Signal Processing # Photometric Stereo

The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion
Yujin Jeong, Won Jeong Ryoo, Da Bin Seo, Wonmin Byeon, Sangpil Kim*, Jinkyu Kim*,
Collaboration : NVIDIA Resaerch
ICCV 2023
[Paper] [Code]
# Generative AI # Audio-guided Video Generation

Dual Policy Learning for Aggregation Optimization in Recommender Systems
Heesoo Jung, Sangpil Kim, Hogun Park*
Collaboration : Sungkyunkwan University
WWW 2023
[Paper]
# Agentic AI # Recommender Systems

ORA3D: Overlap Region Aware Multi-view 3D Object Detection
Wonseok Roh, Gyusam Chang, Seokha Moon, Giljoo Nam, Chanyoung Kim, Younghyun Kim, Jinkyu Kim*, Sangpil Kim*
Collaboration : META Reality Lab, Hyundai
BMVC 2022
[Paper][Project]
# Autonomous Driving # Object Detection

Sound-Guided Semantic Video Generation
Seunghyun Lee, Gyeongrok Oh, Wonmin Byeon, Wonjeong Ryoo, Sang Ho Yoon, Jinkyu Kim*, Sangpil Kim*
Collaboration : NVIDIA Resaerch
ECCV 2022
[Paper][Project] [Code]
# Generative AI # Video Generation

Sound-Guided Semantic Image Manipulation
Seunghyun Lee, Wonseok Roh, Wonmin Byeon, SangHo Yoon, Jinkyu Kim*, Sangpil Kim*
Collaboration : NVIDIA Resaerch, KAIST
CVPR 2022
[Paper][Project] [Code]
# Generative AI # Image Manipulation

Sound-Guided Semantic Image Manipulation
Seunghyun Lee, SangHo Yoon, Jinkyu Kim*, Sangpil Kim*
Collaboration : KAIST
NeurIPSW 2021
[Paper]
# Generative AI # Image Manipulation

Audio-Guided Image Manipulation for Artistic Paintings
Seunghyun Lee, Nahyuk Lee, Chanyoung Kim, Wonjeong Ryoo, Jinkyu Kim, SangHo Yoon*, Sangpil Kim*
Collaboration : KAIST
NeurIPSW 2021
# Generative AI # Image Manipulation

A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks
Sangpil Kim^†, Hyung-gun Chi^†, Xiao Hu, Qixing Huang, Karthik Ramani
ECCV 2020
[Paper] [Dataset A] [Dataset B]

First-Person View Hand Segmentation of Multi-Modal Hand Activity Video Dataset
Sangpil Kim, Hyung-gun Chi, Xiao Hu, Anirudh Vegesana, Karthik Ramani
BMVC 2020
[Paper]

Object Synthesis by Learning Part Geometry with Surface and Volumetric Representations
Sangpil Kim, Hyung-gun Chi, Karthik Ramani
Computer-Aided Design 2020
[Paper]

Enet: A deep neural network architecture for real-time semantic segmentation
Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello
arxiv 2016
[Paper]

Learning hand articulations by hallucinating heat distribution
Chiho Choi, Sangpil Kim, Karthik Ramani
ICCV 2017
[Paper]

Latent transformations neural network for object view synthesis
Sangpil Kim, Winovich Nick, Hyung-gun Chi, Guang Lin, Karthik Ramani
Visual Computer 36 1663-1677 2020
[Paper]