Hongsuk Choi

8 papers · 2020–2025 · 5 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 · Silver 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (14) 🐣 Hot Topic Early Bird

Venues

CVPR (4) CoRL (1) ECCV (1) ICLR (1) WACV (1)

Top co-authors

Kyoung Mu Lee (5) Gyeongsik Moon (5) Joonkyu Park (2) Anthony Zhang (2) Angjoo Kanazawa (2) Jitendra Malik (2) Junyi Zhang (1) Trevor Darrell (1) Ju Yong Chang (1) Chung Min Kim (1)

Research topics

Computer Vision (7) Analysis (5) Deep Learning (4) Artificial Intelligence (2) Machine Learning (2) Core AI (2) Learning Types · Machine Learning (2) Learning Types · Deep Learning (2) Robotics (1) Architectures (1) Capabilities (1) Generation (1) Models (1) Processing (1)

Keywords

human pose estimation (2) 3d human pose estimation (2) self-supervised learning (1) video understanding (1) hand pose estimation (1) shape estimation (1) video analysis (1) text-to-image generation (1) humanoid robot (1) 3d pose estimation (1) occlusion handling (1) structure from motion (1) feature learning (1) diffusion model (1) latent space (1) text-to-image diffusion (1) temporal consistency (1) video processing (1) camera pose estimation (1) representation learning (1)

Papers

FineControlNet: Fine-Level Text Control for Image Generation with Spatially Aligned Text Control Injection WACV 2025 Reconstructing People, Places, and Cameras CVPR 2025 Visual Imitation Enables Contextual Humanoid Control CoRL 2025 Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation ICLR 2023 HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network CVPR 2022 Learning To Estimate Robust 3D Human Mesh From In-the-Wild Crowded Scenes CVPR 2022 Beyond Static Features for Temporally Consistent 3D Human Pose and Shape From a Video CVPR 2021 Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose ECCV 2020