4 papers
SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Models
Mingxiao Tu, Shuchang Ye, Hoijoon Jung +1
Generating high-quality, photorealistic textures for 3D human avatars remains a fundamental yet challenging task in computer vision and multimedia field. However, real paired front…
Patient4D: Temporally Consistent Patient Body Mesh Recovery from Monocular Operating Room Video
Mingxiao Tu, Hoijoon Jung, Alireza Moghadam +2
Recovering a dense 3D body mesh from monocular video remains challenging under occlusion from draping and continuously moving camera viewpoints. This configuration arises in surgic…
Multi-modal 3D Pose and Shape Estimation with Computed Tomography
Mingxiao Tu, Hoijoon Jung, Alireza Moghadam +5
In perioperative care, precise in-bed 3D patient pose and shape estimation (PSE) can be vital in optimizing patient positioning in preoperative planning, enabling accurate overlay…
Beyond Calibration: Confounding Pathology Limits Foundation Model Specificity in Abdominal Trauma CT
Jineel H Raythatha, Shuchang Ye, Jeremy Hsu +1
Purpose: Translating foundation models into clinical practice requires evaluating their performance under compound distribution shift, where severe class imbalance coexists with he…