Showing 2026Show all
3 papers · 1 filter
cs.CV2026
GraspHOI: Full-Body 3D Human-Object Reconstruction with Finger-Level Grasps from a Single In-the-Wild Image
Semin Kim, Haechan Shin, Jongyoo Kim
Existing monocular full-body 3D human-object interaction (HOI) methods do not combine explicit finger-level grasp optimization with category-agnostic object reconstruction. Despite…
cs.CV2026
Root-Selecting Fixed-Point Inversion for Rectified Flows via Trajectory Straightness
Semin Kim, Jihwan Yoon, Seunghoon Hong
Finding the initial noise that generates a given data sample, known as inversion, is a key component for downstream applications such as training-free image editing. Existing fixed…
cs.CV2026
Training-Free Refinement of Flow Matching with Divergence-based Sampling
Yeonwoo Cha, Jaehoon Yoo, Semin Kim +3
Flow-based models learn a target distribution by modeling a marginal velocity field, defined as the average of sample-wise velocities connecting each sample from a simple prior to…