13 papers
SplitAdapter: Load-Aware Humanoid Loco-Manipulation via Factorized Adaptation
Jeonguk Kang, Hanbyel Cho, Sanghyun Kang +1
Humanoid loco-manipulation requires stable whole-body control under varying object masses and pickup/placement heights. This becomes particularly challenging in sim-to-real transfe…
SafeFlow: Real-Time Text-Driven Humanoid Whole-Body Control via Physics-Guided Rectified Flow and Selective Safety Gating
Hanbyel Cho, Sang-Hun Kim, Jeonguk Kang +1
Recent advances in real-time interactive text-driven motion generation have enabled humanoids to perform diverse behaviors. However, kinematics-only generators often exhibit physic…
Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation
Yooshin Cho, Hanbyel Cho, Janghyeon Lee +3
As the use of artificial intelligence rapidly increases, the development of trustworthy artificial intelligence has become important. However, recent studies have shown that deep n…
Video Inference for Human Mesh Recovery with Vision Transformer
Hanbyel Cho, Jaesung Ahn, Yooshin Cho +1
Human Mesh Recovery (HMR) from an image is a challenging problem because of the inherent ambiguity of the task. Existing HMR methods utilized either temporal information or kinemat…
Instruct-4DGS: Efficient Dynamic Scene Editing via 4D Gaussian-based Static-Dynamic Separation
Joohyun Kwon, Hanbyel Cho, Junmo Kim
Recent 4D dynamic scene editing methods require editing thousands of 2D images used for dynamic scene synthesis and updating the entire scene with additional training loops, result…
Foreseeing Reconstruction Quality of Gradient Inversion: An Optimization Perspective
HyeongGwon Hong, Yooshin Cho, Hanbyel Cho +2
Gradient inversion attacks can leak data privacy when clients share weight updates with the server in federated learning (FL). Existing studies mainly use L2 or cosine distance as…
Generative Approach for Probabilistic Human Mesh Recovery using Diffusion Models
Hanbyel Cho, Junmo Kim
This work focuses on the problem of reconstructing a 3D human body mesh from a given 2D image. Despite the inherent ambiguity of the task of human mesh recovery, most existing work…
Implicit 3D Human Mesh Recovery using Consistency with Pose and Shape from Unseen-view
Hanbyel Cho, Yooshin Cho, Jaesung Ahn +1
From an image of a person, we can easily infer the natural 3D pose and shape of the person even if ambiguity exists. This is because we have a mental model that allows us to imagin…
Localization using Multi-Focal Spatial Attention for Masked Face Recognition
Yooshin Cho, Hanbyel Cho, Hyeong Gwon Hong +4
Since the beginning of world-wide COVID-19 pandemic, facial masks have been recommended to limit the spread of the disease. However, these masks hide certain facial attributes. Hen…
Rethinking Efficacy of Softmax for Lightweight Non-Local Neural Networks
Yooshin Cho, Youngsoo Kim, Hanbyel Cho +3
Non-local (NL) block is a popular module that demonstrates the capability to model global contexts. However, NL block generally has heavy computation and memory costs, so it is imp…
Stochastic Attribute Modeling for Face Super-Resolution
Hanbyel Cho, Yekang Lee, Jaemyung Yu +1
When a high-resolution (HR) image is degraded into a low-resolution (LR) image, the image loses some of the existing information. Consequently, multiple HR images can correspond to…
Camera Distortion-aware 3D Human Pose Estimation in Video with Optimization-based Meta-Learning
Hanbyel Cho, Yooshin Cho, Jaemyung Yu +1
Existing 3D human pose estimation algorithms trained on distortion-free datasets suffer performance drop when applied to new scenarios with a specific camera distortion. In this pa…
Improving Generalization of Batch Whitening by Convolutional Unit Optimization
Yooshin Cho, Hanbyel Cho, Youngsoo Kim +1
Batch Whitening is a technique that accelerates and stabilizes training by transforming input features to have a zero mean (Centering) and a unit variance (Scaling), and by removin…