5 papers
How Noisy Poses Break Inverse Dynamics: Analysis and Mitigation for Video-Based Joint Torque Estimation
Donghyun Kim, Chanyoung Kim, Eunseo Jeong +2
Recent advances in monocular 3D human pose estimation enable accurate body tracking from video. However, translating these kinematic estimates into physical quantities, such as joi…
Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph
Donghyun Kim, Chanyoung Kim, Youngjoong Kwon +1
Reconstructing building wireframe from airborne LiDAR point clouds yields a compact, topology-centric representation that enables structural understanding beyond dense meshes. Yet…
PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling
Donghyun Kim, Hyeonkyeong Kwon, Yumin Kim +1
3D point clouds are increasingly vital for applications like autonomous driving and robotics, yet the raw data captured by sensors often suffer from noise and sparsity, creating ch…
Parameter Efficient Fine Tuning for Multi-scanner PET to PET Reconstruction
Yumin Kim, Gayoon Choi, Seong Jae Hwang
Reducing scan time in Positron Emission Tomography (PET) imaging while maintaining high-quality images is crucial for minimizing patient discomfort and radiation exposure. Due to t…
DragText: Rethinking Text Embedding in Point-based Image Editing
Gayoon Choi, Taejin Jeong, Sujung Hong +1
Point-based image editing enables accurate and flexible control through content dragging. However, the role of text embedding during the editing process has not been thoroughly inv…