activity
20242026
collaborators

5 papers

cs.CV2026

AHS: Adaptive Head Synthesis via Synthetic Data Augmentations

Taewoong Kang, Hyojin Jang, Sohyun Jeong +4

Recent digital media advancements have created increasing demands for sophisticated portrait manipulation techniques, particularly head swapping, where one's head is seamlessly int…

cs.RO2025

ACG: Action Coherence Guidance for Flow-based Vision-Language-Action models

Minho Park, Kinam Kim, Junha Hyung +5

Diffusion and flow matching models have emerged as powerful robot policies, enabling Vision-Language-Action (VLA) models to generalize across diverse scenes and instructions. Yet,…

cs.CV2025

Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models

Sungwon Hwang, Hyojin Jang, Kinam Kim +2

Fine-tuning Video Diffusion Models (VDMs) at the user level to generate videos that reflect specific attributes of training data presents notable challenges, yet remains underexplo…

cs.CV2025

Zero-Shot Head Swapping in Real-World Scenarios

Taewoong Kang, Sohyun Jeong, Hyojin Jang +1

With growing demand in media and social networks for personalized images, the need for advanced head-swapping techniques, integrating an entire head from the head image with the bo…

cs.GR2024

SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars

Jaeseong Lee, Taewoong Kang, Marcel C. Bühler +5

Recent advancements in head avatar rendering using Gaussian primitives have achieved significantly high-fidelity results. Although precise head geometry is crucial for applications…