Seokhyeon Hong

Hello, world! I am a Ph.D. student at KAIST Visual MediaLab, advised by Prof. . My research interests lie in computer graphics and character animation, including generation, editing, in-betweening, retargeting, rigging, and all the fun stuff that makes characters move.

Email  /  CV  /  Scholar  /  Github  /  Blog  /  YouTube

profile photo

Experiences

Microsoft Microsoft
Research Intern (Jun 2026 - Sep 2026)

Publications

PontTuset Skinned Motion Retargeting via Artifact-driven Kinematic Prior Refinement
, , , ,
(* equal contribution)
SIGGRAPH Asia 2026; ACM Transactions on Graphics (TOG)
project page / paper / code / video

Skinned motion retargeting by explicit artifact observation and refinement of pre-trained kinematic prior.

PontTuset ReCHOIR: Contact-guided Human Object Interaction Retargeting to Diverse Characters
, , , , ,
SIGGRAPH Asia 2026; ACM Transactions on Graphics (TOG)
project page / paper / video

Retargeting human-object interaction motion sequences to diverse characters while maintaining interaction fidelity.

PontTuset Length-varying Neural Motion Stitching via Cluster Transition Graph
, , , ,
SIGGRAPH Asia 2026; ACM Transactions on Graphics (TOG)
To-be-released

Connecting two motion sequences with the shortest motion path using a cluster transition graph constructed by VQ-VAE.

PontTuset Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation
, ,
(* equal contribution)
SIGGRAPH 2026
project page / paper / code / video

Hypernetwork-driven low-rank adaptation for flexible and efficient stylized text-to-motion generation with robustness to unseen styles.

PontTuset Skinned Motion Retargeting with Spatially Adaptive Interaction Guidance
, , , , ,
SIGGRAPH 2026; ACM Transactions on Graphics (TOG)
project page / paper / code (coming soon) / video
PontTuset X-AVDT: Audio-Visual Cross-Attention for Robust Deepfake Detection
, , , , ,
CVPR 2026
project page / paper / code / video

Robust deepfake detection method and cross-generator dataset by leveraging cross-attention features to capture audio-visual correlations.

SALAD: Skeleton-aware Latent Diffusion for Text-driven Motion Generation and Editing
, , , , ,
CVPR 2025
project page / paper / code / video

Skeleton-aware latent diffusion that incorporates interactions between skeletal joints, motion frames, and textual words for text-driven motion generation and zero-shot editing.

AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models
, , ,
CVPR 2025
project page / paper / code

Motion in-betweening for arbitrary characters using video diffusion models fine-tuned with ICAdapt and motion-video mimicking, recuding dependency on character-specific datasets.

PontTuset ASMR: Adaptive Skeleton-Mesh Rigging and Skinning via 2D Generative Prior
, , , ,
(* equal contribution)
Eurographics 2025; Computer Graphics Forum (CGF)
project page / paper / code / video

Rigging and skinning 3D character meshes by leveraging cross-attention modules and 2D generative priors for robust generalization across diverse skeletal and mesh configurations.

PontTuset Geometry-Aware Retargeting for Two Skinned Characters Interaction
, , , ,
SIGGRAPH Asia 2024; ACM Transactions on Graphics (TOG)
project page / paper / video

Retargeting interaction motions of two skinned characters via sparse mesh-agnostic geometry representations and spatio-cooperative transformers.

PontTuset Long-term Motion In-betweening via Keyframe Prediction
, , ,
SCA 2024; Computer Graphics Forum (CGF)
paper / code / video

Keyframe prediction using two-stage hierarchical transformers for long-term motion in-betweening.

PontTuset Recurrent Motion Refiner for Locomotion Stitching
, , ,
Eurographics 2024; Computer Graphics Forum (CGF)
paper / video

Training a recurrent motion refiner for neural locomotion stitching.

Projects

aPyOpenGL aPyOpenGL
github

A python library for motion data processing with nice-looking visualization using OpenGL. It provides several functionalities not only motion-related functions (e.g. forward kinematics) but also auxiliary functions such as rotation conversion, file I/O, visualization with skinned mesh, and more. Most of my research projects have utilized this library for data processing and visualization.