6 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…
Rethinking Graph Convolution for 2D-to-3D Hand Pose Lifting
Chanyoung Kim, Donghyun Kim, Dong-Hyun Sim +2
Graph convolutional networks (GCNs) are widely used for 3D hand pose estimation, where the hand skeleton is encoded as a fixed adjacency graph. We revisit whether this is the most…
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…
GenFusion: Feed-forward Human Performance Capture via Progressive Canonical Space Updates
Youngjoong Kwon, Yao He, Heejung Choi +4
We present a feed-forward human performance capture method that renders novel views of a performer from a monocular RGB stream. A key challenge in this setting is the lack of suffi…
Repurposing 2D Diffusion Models for 3D Shape Completion
Yao He, Youngjoong Kwon, Tiange Xiang +2
We present a framework that adapts 2D diffusion models for 3D shape completion from incomplete point clouds. While text-to-image diffusion models have achieved remarkable success w…
Artist-Created Mesh Generation from Raw Observation
Yao He, Youngjoong Kwon, Wenxiao Cai +1
We present an end-to-end framework for generating artist-style meshes from noisy or incomplete point clouds, such as those captured by real-world sensors like LiDAR or mobile RGB-D…