Gwanghyun Kim
8 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Conference Polyglot (4) π£ Hot Topic Early Bird π Cross-Pollinator (15) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (14)
π§
Keyword Pioneer
π
Keyword Champion
(2)
π₯
Unstoppable
(5)
Conferences
ICCV (3)
CVPR (2)
NIPS (2)
ECCV (1)
Top co-authors
Keywords
diffusion model
(5)
domain adaptation
(2)
3d generative model
(2)
text-to-image diffusion
(2)
occlusion handling
(1)
latent diffusion
(1)
video diffusion
(1)
temporal consistency
(1)
identity preservation
(1)
image manipulation
(1)
domain gap
(1)
pose conditioning
(1)
normal estimation
(1)
metric depth
(1)
human body generation
(1)
3d human modeling
(1)
diversity preservation
(1)
text-image correspondence
(1)
image-to-video diffusion
(1)
human geometry estimation
(1)
Papers
GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion
ICCV 2025
PersonaCraft: Personalized and Controllable Full-Body Multi-Human Scene Generation Using Occlusion-Aware 3D-Conditioned Diffusion
ICCV 2025
BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion
ECCV 2024
A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
NIPS 2024
PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion
ICCV 2023
DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model
CVPR 2023
DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation
CVPR 2022
Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis
NIPS 2021