Skip to content
conftrace_

Gwanghyun Kim

9 papers · 2021–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
+3 more ↓ 🌍 Conference Polyglot Β· Bronze πŸƒ Academic Marathon Β· Sprint πŸŒ‰ Interdisciplinary Bridge Β· Bronze πŸ—ΊοΈ Taxonomy Completionist (15) 🐣 Hot Topic Early Bird
🧭 Keyword Pioneer 🧬 Topic Evolution πŸ”₯ Unstoppable Β· Bronze

Venues

CVPR (3) ICCV (3) NeurIPS (2) ECCV (1)

Top co-authors

Se Young Chun (6) Suh Yoon Jeon (2) Jong Chul Ye (2) Koki Nagano (1) Xueting Li (1) Umar Iqbal (1) Hoigi Seo (1) Tianye Li (1) Ye Yuan (1) Krishna Somandepalli (1)

Research topics

Deep Learning (8) Models (7) Computer Vision (6) Generation (4) Machine Learning (3) Analysis (3) Artificial Intelligence (2) Application Areas (2) Architectures (2) Core AI (2) Learning Types (2) Healthcare & Medicine (1) Clinical (1) Learning Paradigms (1) Processing (1)

Keywords

diffusion model (6) text-to-image diffusion (2) 3d generative model (2) domain adaptation (2) image generation (1) medical imaging (1) depth estimation (1) image synthesis (1) occlusion handling (1) collaborative learning (1) latent diffusion (1) video diffusion (1) temporal consistency (1) identity preservation (1) audio-visual generation (1) chest x-ray (1) image manipulation (1) split learning (1) domain gap (1) pose conditioning (1)

Papers

Human Interaction-Aware 3D Reconstruction from a Single Image CVPR 2026 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 A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation NeurIPS 2024 BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion ECCV 2024 DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model CVPR 2023 PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion ICCV 2023 DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation CVPR 2022 Federated Split Task-Agnostic Vision Transformer for COVID-19 CXR Diagnosis NeurIPS 2021