KunHo Heo — accepted AI-conference papers

2026

ParTY: Part-Guidance for Expressive Text-to-Motion Synthesis

KunHo Heo, SuYeon Kim, Yonghyun Gwon, Youngbin Kim, MyeongAh Cho

CVPR 2026

Text-to-motion synthesis aims to generate natural and expressive human motions from textual descriptions. While existing approaches primarily focus on generating holistic motions from text descriptions, they struggle to accurately reflect actions involving specific body parts. Recent part-wise motio

Cited by 0 Source ↗Scholar ↗

2025

Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction

KunHo Heo, GiHyeon Kim, SuYeon Kim, MyeongAh Cho

NeurIPS 2025poster

3D Semantic Scene Graph Prediction aims to detect objects and their semantic relationships in 3D scenes, and has emerged as a crucial technology for robotics and AR/VR applications. While previous research has addressed dataset limitations and explored various approaches including Open-Vocabulary se…

Cited by 0 Source ↗code ↗Scholar ↗