Professor
- Kyungdon Joo
Students & Researchers
- Changwoo Kang (github)
- Hyungyu Park (github)
- Inha Lee (github)
- Jaehyeok Shim (github)
- Gyeongsu Cho (github)
- Jongsung Lee (github)
- Sangjune Park (github, homepage)
- Junsu Kim (github)
- Junhee Lee (github)
- Youngwoo Jeon (github)
- Jaehun Bang (github)
- Minji Kim (github)
- Jeongeon Lee (github)
- Taehun Ryu (github)
- Yujin Park (github)
- Ganghyeon Lee (github)
- Inhyeok Choi (github)
- Chanwoo Lee (github)
- Seunghyeon Seo (github)
- Seungheon Jeong (github)
- Dongjae Jeong (github)
- Chaeeun Moon (github)
- Juhan Oh (github)
- Aron Lee (github)
- Jeonghwan Lee (github, blog)
- Dongkyu Doo (github)
- Sebin Lee (github, homepage)
Alumni
- Minseok Kim (github)
- Jeongin Park (github)
- Kyongjun Kim (github)
- Jaehoon Jang (github)
- Harin Park (github)
- Minje Kim (github)
- Jinhyeok Kim (github)
- Seungoh Han (github)
- Yongjun Choi (github, homepage)
[TMLR 2026] Trip-to-Gaussian: A Versatile Framework for Unconditional 3D Generation
[ECCV 2026] UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization
[ECCV 2026] FeDepth: Federated Learning for Depth Estimation under Robot Heterogeneity
[CVPR 2026] From Corners to Fiducial Tags: Revisiting Checkerboard Calibration for Event Cameras
[CVPR 2026] LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds
[ICRA 2026] Prior-Constrained Explorative Guidance for Generalization in Diffusion Motion Planning
[WACV 2026] Not Like Transformers: Drop the Beat Representation for Dance Generation with Mamba-Based Diffusion Model
[WACV 2026] LighthouseGS: Indoor Structure-aware 3D Gaussian Splatting for Panorama-Style Mobile Capture
[WACV 2026] AnyBald: Toward Realistic Diffusion-Based Hair Removal In-The-Wild
[WACV 2026] Beyond the Highlights: Video Retrieval with Salient and Surrounding Contexts
[WACV 2026] Pose-Diverse Multi-View Virtual Try-on from a Single Frontal Image via Diffusion Transformer
[SIGGRAPH Asia 2025] DeformSplat: Rigidity-Aware 3D Gaussian Deformation from a Single Image
[IROS 2025] VPOcc: Exploiting Vanishing Point for 3D Semantic Occupancy Prediction
[IJCV 2025] DogRecon: Canine Prior-Guided Animatable 3D Gaussian Dog Reconstruction From A Single Image
[CVPR 2025] HUSH: Holistic Panoramic 3D Scene Understanding using Spherical Harmonics
[RA-L 2024] A Benchmark Dataset for Collaborative SLAM in Service Environments
[CVPR 2024] DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction
[RA-L 2024] AiSDF: Structure-aware Neural Signed Distance Fields in Indoor Scenes
[ICASSP 2024] Fracture Assembly with Segmentation and Iterative Registration
[AAAI 2024] ContactGen: Contact-Guided Interactive 3D Human Generation for Partners
[ICCV 2023] SlaBins: Fisheye Depth Estimation using Slanted Bins on Road Environments
[CVPR 2023] Diffusion-based Signed Distance Fields for 3D Shape Generation
[AAAI 2023] Pose-guided 3D Human Generation in Indoor Scene