Seunghwan Lee

4 papers · 2021–2025 · 2 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 ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (18)

Venues

CVPR (3) ICCV (1)

Top co-authors

Aecheon Jung (1) C. Karen Liu (1) Antoine Falisse (1) Seungyeob Han (1) Han Joo Chae (1) Hyewon Son (1) Tae Hyun Kim (1) Donghyeon Cho (1) Tom Van Wouwe (1) Youngeun Kim (1)

Research topics

Computer Vision (3) Deep Learning (3) Machine Learning (3) Analysis (2) Learning Types · Machine Learning (2) Healthcare & Medicine (1) Robotics (1) Application Areas (1) Capabilities (1) Clinical (1) Domain-Specific (1) Generation (1) Learning Types · Deep Learning (1) Models (1) Processing (1)

Keywords

3d reconstruction (1) semantic segmentation (1) self-supervised learning (1) medical imaging (1) video restoration (1) model merging (1) sensor fusion (1) human motion (1) motion capture (1) diffusion model (1) memory efficiency (1) point cloud processing (1) quantization error (1) fully convolutional network (1) inertial measurement unit (1) motion reconstruction (1) video denoising (1) autoregressive inference (1) task vector quantization (1) fine-tuned checkpoint (1)

Papers

Task Vector Quantization for Memory-Efficient Model Merging ICCV 2025 DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion CVPR 2024 Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction To Treat Diabetic Foot Ulcers CVPR 2022 Restore From Restored: Video Restoration With Pseudo Clean Video CVPR 2021